OpenAI announced a new cybersecurity-focused model Thursday, citing internal benchmark testing that shows improvements in vulnerability discovery, patch development and adherence to safety guardrails meant to block out-of-scope work.

GPT-6 Cyber will first be available to a limited number of customers in OpenAI’s Daybreak Red program, which uses more advanced or nonpublic cybersecurity models for offensive red teaming.

As a preview of the model’s capabilities, OpenAI officials said GPT-6 has found at least 81 “novel” vulnerabilities in the Firefox web browser, developed exploits for 948 Linux kernel vulnerabilities and was able to develop and validate a critical remote code execution vulnerability in Brotli, a popular open-source data compression tool. All the vulnerabilities were reported to owners and patched.

OpenAI officials told reporters Wednesday that the new safeguards include additional identity and account security requirements, more frequent check-ins from the model to OpenAI when a request is made to perform high-risk behaviors, and additional monitoring for “misalignment” or rule-breaking.

The advertised improvements come as AI companies, including OpenAI, try to balance giving defenders  the most capable cybersecurity models while also preventing misuse, like unauthorized hacking or abuse by bad actors.

Eric Wallace, a researcher at OpenAI who focuses on training, evaluation and sandboxing for new models, said part of the training for GPT-6 Cyber included a simulated evaluation meant to mimic the Hugging Face incident, where the company’s models escaped internal sandbox testing environments and hacked into part of a major online AI code repository.  

“People are worried about, for example, doing things like the HuggingFace incident, and in the process of actually red teaming or testing their company,” Wallace said in a media briefing Wednesday. “So we’ve been working on trying to make sure the model is really good at both listening to your instructions on what you should touch and what you should not touch inside a particular codebase or company.”

Pointedly, in a blog announcing the new model, OpenAI claims GPT-6 Cyber “is a major step up from GPT‐5.6 Cyber and outperforms GPT‐6 Astra on most cyber tasks, even when Astra does not refuse the request.”

Wallace said since the summer, when OpenAI’s 5.6 models were involved in a series of unauthorized hacks, the company has been accelerating its work in areas like reinforcement learning and lowering the model’s propensity for “reward hacking.”

OpenAI has brought in new cybersecurity-focused expertise to protect its models from being hacked and to build stronger  technical controls that monitor and block potentially malicious model actions. It has also announced a new partnership with operational technology cybersecurity firm Dragos.

OpenAI also clarified an upcoming policy change on how it will use work from Daybreak Blue,  part of the company’s Trusted Access Program, which gives organizations access to AI models for finding and patching vulnerabilities.

Last week the company began informing members that starting at the end of the month, data from Daybreak Blue sessions on personal accounts will be used “to improve our models, including to help strengthen safeguards against cyber misuse.” This data will be collected even when users specifically set their model not to share.

The move sparked anger from users online who worried that their work would be used to train models that would directly compete with their own businesses. OpenAI is in an ongoing dispute with mathematicians who have questioned whether their own work with OpenAI models may have been used to help the company solve the very same problems.

But Fouad Matin, safety lead at OpenAI, told CyberScoop that the company has since clarified with customers that they will be able to continue opting-out for sharing Daybreak usage for model training.

Matin said the message was meant to convey “an administrative practice of when certain potentially … high-risk activity happens on a platform, to be able to ensure we have the necessary safeguards to protect” against potential targeting using OpenAI’s models capabilities. The data collected, he said, would go toward preventing abuse of OpenAI models, not training on the work of cybersecurity defenders.

“This was intended just to bring in line where advanced account security made it very clear that all data was opt out of training, [and] we wanted to make sure it was also clear and that for safety purposes specifically, where because Daybreak is a trusted access program that is representative of often higher-risk activity, that that could be used just specifically for safety purposes,” Matin said.

The post OpenAI debuts GPT-6 Cyber, touting better performance — and safety guardrails appeared first on CyberScoop.

Apple has sent new notifications of mercenary spyware infections to almost 100 countries, with recipients including journalists and documentary filmmakers.

“Today’s notification is being sent to targeted users in 99 countries, and to date we have notified users in over 150 countries in total,” the company said. “The extreme cost, sophistication, and worldwide nature of mercenary spyware attacks make them some of the most advanced digital threats in existence today. As a result, Apple does not attribute the attacks or the notice you’re receiving to any specific attackers or geographical regions.”

Apple didn’t immediately respond to a request for comment Friday about the countries targeted. Researchers and groups that work on spyware said the notifications were significant, however.

“This again promises to be an important set of notifications with a bunch of cases, based purely on what we see publicly,” said John Scott-Railton, senior researcher at The Citizen Lab at the University of Toronto. He also posted on social media about how potential victims could defend themselves, warning people to be cautious about companies that offer paid solutions to spyware infections.

He cautioned that the lack of notification doesn’t rule out an infection. The steps Apple recommends, which Scott-Railton seconded, were to enable Lockdown Mode and to get in touch with the digital rights group Access Now.

“The number of Apple threat notifications we are seeing from countries around the world indicates that the fight against the scourge of spyware abuse is far from over,” said Natalia Krapiva, senior tech-legal counsel with Access Now. “While we have increased our capacity to investigate spyware abuse, and companies like Apple have done a lot to notify and protect people from it, repressive states continue to use these powerful surveillance technologies, including against civil society actors and opposition figures.”

Apple sent its last major batch of notifications in August. The notifications frequently lead to victims approaching Access Now, The Citizen Lab and other groups seeking further assistance and prompting deeper investigations.

The notifications come shortly before the final rounds of negotiations over industry standards for commercial hacking tools being developed under the voluntary Pall Mall Process. The industry guidelines follow an earlier set of guidelines catered to governments.

“The states that will ultimately adopt these guidelines must come to terms that the current system is not working, and that the spyware industry must face some real consequences for the uncontrolled sale of these tools and refusal to curb the abuses,” Krapiva said.

The post Apple notifications alert victims in 99 countries about mercenary spyware infections appeared first on CyberScoop.

A company working on behalf of the Department of Homeland Security sought to cut off online access to information on more than 41,000 employees that hacktivists said they obtained from a database breached at DHS.

A search tool for the database, named Icepick, went offline for a spell before coming online again Thursday under a different registrar.

Icelandic hosting company FlokiNET said Thursday that it received a request from DHS contractor ZeroFox to remove the data, which it refused.

“By mid-morning, icepi.cx no longer resolved. Its registrar, CentralNic, had placed the domain on serverHold,” FlokiNET said in a blog post. “Our refusal kept nothing online. The request that decided the outcome to take the site down was not the one sent to us. A registrar reached the opposite conclusion the same morning, published nothing, and a global audience lost access to the site. In the meantime the site is online again under a domain from a different registrar.”

CentralNic and ZeroFox did not immediately respond to requests for comment Thursday.

DHS said late Wednesday that it was working to protect its employees against any breach.

“DHS is aware of a potential breach and is actively working to address the situation swiftly and effectively,” a spokesperson said. “We take all security threats against our employees and officers seriously and will work to ensure all are properly protected. We will update the public when more information is available.”

The social media site Bluesky was also blocking links to the archive because it shared people’s contact information without their permission, although a company official said changes were coming because the wording had identified it as a malicious link.

FlokiNET said it refused the ZeroFox request that mislabeled the archive as part of a doxxing campaign.

“Doxxing publishes private details about private people so that others can find them at home. Icepick publishes work identities of government employees,” it wrote. “Who they work for. What their role is. How they can be reached in that role. The information describes people in the exercise of public authority, not in their private lives. Federal officers carrying out an enforcement programme are not private individuals while they are carrying it out.”

“The public has a legitimate interest in knowing who is doing that work, under whose authority, and in which office,” it continued. “Journalists cannot report on an agency whose personnel are structurally unknowable.”

ZeroFox said that regardless of that, the data made it possible to locate people whose information was in the database.

“The request does not depend on who the listed individuals are or what their duties are,” ZeroFox wrote to FlokiNET. “It rests on two facts: the data was stolen, and it is personal data that identifies and locates real people.”

The post Leaked DHS employee archive, Icepick, faces challenges to stay online appeared first on CyberScoop.

Anthropic said its AI systems could drastically reshape the software and cybersecurity sectors in the “near term,” while also laying out a litany of cybersecurity and regulatory risks facing the company as it prepares to go public.

In a filing with the Securities and Exchange Commission ahead of its initial public offering, the company said its technology could transform entire industries and the economy. Already, cybersecurity-focused models by Anthropic and rival OpenAI can find and exploit cybersecurity vulnerabilities at an alarming speed.

But the company also acknowledged serious risks its models, including Claude, pose to itself, its users and the world. Hacks by bad actors using Claude or AI agents could cause financial, legal or physical damage, spark lawsuits and affect Anthropic’s ability to insure against future losses. 

Anthropic expects bad actors, including foreign governments, to increase their efforts to access its latest frontier models as their cybersecurity capabilities improve. That creates persistent risk, since its models could be used in cyberattacks carried out by foreign governments and cybercriminal groups.

“Any successful attempt to misuse, or any perceived misuse of, our models, platform, and applications for a cyberattack or for any other malicious purpose could result in exposure to liability, disruption of our customer or other commercial relationships, or damage to our reputation,” Anthropic said in its filing.

That potential legal and regulatory risk extends to independent security researchers and others who have “used, and may in the future use, our models to identify and exploit vulnerabilities in the systems of other companies, including other AI developers, at times in connection with authorized bug bounty programs.”

Anthropic cited the rise of AI-enabled cybersecurity incidents in the U.S., the U.K. and other countries, saying they could result in more adversarial regulatory environments around the world. European laws, for example, require detailed breach reports within a strict time frame, which could be difficult for Anthropic to meet.

Federal intervention could also disrupt AI development and release timelines. Anthropic cited the Department of Commerce placing export controls on its Mythos 5 and Fable 5 models, and confirmed that the Federal Trade Commission issued it a civil investigative demand earlier this month for more information on the safety and security of its products, as well as its consumer, data and privacy protection policies.

AI development will be guided by more than ethics

Anthropic has developed a public reputation as an ethics-first AI company,  most notably in disputes with the Department of Defense over how its models are used in wartime. But the IPO filing states the company must “balance safety considerations against commercial objectives, competitive pressures, and stakeholder expectations.”

The company also said it is “actively” improving security infrastructure and controls. It also has acknowledged it has moved forward on projects with “known limitations or gaps in our defenses” and may do so again.

“There can be no assurance, however, that the safeguards or access regimes we adopt will prove adequate, that we will correctly identify which capabilities require restriction, or that constraints we impose will not be circumvented,” the document stated.

AI agents can create new and “distinct” cybersecurity attack surfaces because they interact with so many other tools, databases, APIs and other third-party systems. That creates  feedback loops between a model and other systems, which can be compromised or manipulated to feed malicious instructions to the agent.

Anthropic suggested the problems could be so pronounced that it may have difficulty obtaining insurance for some cybersecurity incidents and data breaches related to its models.  

Andrew Yoon, head of research at the nonprofit CivAI, told CyberScoop that both the document and Anthropic’s overall record show a company that has consistently put profit considerations over building safer AI.

“I think in general they’re not meeting the moment here,” Yoon said. “Despite all of these risks that they flagged, they’re moving ahead pretty much as fast as humanly possible, and their justification for this is ‘You can’t do safety from second place.’”

Yoon said Anthropic has not only pushed its own frontier research toward dangerous and harmful capabilities like hacking, “they are pushing very aggressively ahead” and in some cases influencing competitors to follow suit. Anthropic’s release of its Mythos and Fable models earlier this year caused OpenAI to shift “its entire corporate strategy” to match the capabilities of Anthropic models in coding, science, and general intelligence by building models at breakneck speed.

“They have pretty directly caused the industry to speed up toward this mad, frenzied race and yet they’re saying ‘Oh, our models are too powerful,’ ”….it just doesn’t add up to me,” said Yoon.

But Yoon said it’s not clear that building AI systems to carry out dangerous, complex activities like hacking or bioweapons is necessary to be competitive in the global marketplace. He pointed to the wide assortment of Chinese-developed, open-weight AI models that are widely used around the world, but are not powerful enough to chain together complex exploits or develop new viruses.  

“This is not an accident, this is not the models generalizing from regular programming capabilities…the labs are intentionally training them on hacking as well,” said Yoon. “This is because they want to offer better defensive capabilities, they want to be able to sell offensive products to the government…and they do pretty cavalier testing with [the models] inside the labs.”

The post All the security risks Anthropic is worried about before its IPO  appeared first on CyberScoop.

Two senators say that revelations about online targeted advertising being used as a vector for spyware infections underscore the need for better security practices in the industry.

Some members of the advertising industry that were subjects of the report, meanwhile, think their practices are up to the task.

The Citizen Lab at the University of Toronto, in partnership with the cybersecurity and ad-tech firm Confiant, last week published a report on AdFection, a technique whereby targeted ads were delivering zero-click mercenary spyware.

“Ad vendors must significantly level up their cybersecurity and threat detection capacity to effectively cut off malicious advertisers across the supply chain,” The Citizen Lab report states. “They must rigorously and regularly vet, screen, and audit their business partners and hold them accountable for their own supply chains.”

In 2023, Democratic Sens. Ron Wyden of Oregon and Cory Booker of New Jersey introduced legislation to ban advertising networks and facilitators from using personal data to target, but the legislation never advanced past introduction. Both said The Citizen Lab report illustrated the need for industry reform.

“The report underscores the growing risk of spyware and the increasingly sophisticated methods used to track and target people online,” Booker said in a statement to CyberScoop. “Americans need vastly stronger privacy protections that stay ahead of these evolving surveillance threats.”

The security threat of targeted online advertising to government devices is of particular concern to Wyden, with his letters to government agencies cited in the report. Wyden has called adtech a national security threat. Ads from Discover-Tech, the company most linked to AdFection, got impressions on government networks.

“Allowing targeted ads on government devices is an open invitation to spies and criminals. It’s the digital equivalent of leaving all the doors and windows unlocked at a sensitive government facility,” he said in a statement to CyberScoop.

“It’s clear that advertising exchanges are not meaningfully protecting users against malware and location tracking, which is why I’ve been urging the government to disable ads on government browsers and turn off mobile ad IDs, and have pushed my bill to ban all targeted advertising,” he continued. “The latest Citizen Lab report is an impressive reminder that this sector simply cannot be trusted to put users’ security ahead of profits.”

A number of U.S. agencies have taken steps to block ads due to the threats they pose, or recommended blocking them for feds.

Discover-Tech appeared on lists of “certified” and “approved” vendors that Google and the advertising industry association IAB Europe maintained. Google participated in the report, but IAB Europe didn’t respond to it until after publication. Both provided additional comments to CyberScoop.

Google and IAB Europe, and the ad networks Beeswax, Vungle and Eskimi all took steps to remove Discover-Tech’s access to the digital advertising ecosystem, according to the report. A mix of other ad systems replied to The Citizen Lab, but some did not, including Microsoft, which owns the ad system Xandr. Microsoft also didn’t respond to requests for comment from CyberScoop.

The Citizen Lab report concluded that the advertising industry displayed “a dangerous lack of due diligence” and criticized “broken digital infrastructure,” while also saying that the sector needed to “get serious” about security.

It said ad vendors needed to better share threat data, improve vetting of partners, audit vendor registries and ban vendors by default in jurisdictions known to be permissive of abuse.

In response to questions from CyberScoop about those conclusions, a Google spokesperson provided a statement.

“We banned Discover Tech during a joint investigation with Citizen Lab and Confiant,” the spokesperson said. “Throughout that work, we continuously blocked malicious ads to help people stay protected while we dismantled the network.”

Google said that its safety teams and systems continuously blocked individual bad ads from Discover-Tech, but banning them entirely from the platform required proof that their ad infrastructure was linked to spyware.

The company also said it regularly audits participants in its Authorized Buyer program, as well as deploying “multi-layered defenses to stop bad ads,” and that its automated systems detected over 99% of policy-violating ads before reaching users last year.

IAB Europe responded more specifically.

“The findings do not demonstrate that the digital advertising infrastructure is broken, but rather point to the potential misuse of existing technologies and functionalities that are not specific to digital advertising but inherent to web technologies,” said Lauren Wakefield, marketing and communications director for the association. “While the industry continuously invests in improving security and safeguards against fraud and other forms of misuse, the investigation of potentially unlawful activities, such as the deployment of spyware, ultimately falls within the remit of competent authorities.”

The Citizen Lab report also urges regulators to take action, including conducting an investigation of Discover-Tech and the spyware firm Candiru, which infect users through Discover-Tech online ads; “more closely scrutinize the advertising ecosystem to determine whether other companies are leveraging it for espionage and spyware delivery, and determine whether they have violated applicable laws and regulations;” and pursue sanctions against mercenary spyware firms and the companies that enable them.

“Preventing fraud and other forms of misuse is already an ongoing priority across the digital advertising ecosystem, and IAB Europe supports industry efforts to invest in technologies, processes and safeguards to identify and mitigate cybersecurity risks,” Wakefield continued. “We hope this report will be seen as an opportunity to reassess and improve existing approaches to cybersecurity. It is important to recognise that cybersecurity requirements and measures must be proportionate to the risks and circumstances of each individual company, which is why one-size-fits-all recommendations may not always be appropriate.”

The post Senators say targeted ads are a security risk. Ad groups say the critics are off base. appeared first on CyberScoop.

Indian certificate authority eMudhra said Thursday it will stop issuing SSL/TLS certificates days after researchers showed that the private keys securing eight of its certificates were so weak they could be reconstructed in under a second.

The announcement closes an incident where major browsers blocked the certificates and  Indian authorities launched an investigation.  

The company said its board concluded after detailed deliberations that leaving the business was the right decision for eMudhra and its shareholders. Company Chairman V. Srinivasan cited rising costs from data sovereignty and compliance requirements, along with competition from large providers that issue the certificates free of charge. He also said social media amplification of the incident brought scrutiny “out of proportion” to the unit’s place in the company.

“For many certifying authorities, SSL/TLS is the whole business,” the company said. “For eMudhra it is one part of a much broader digital solutions portfolio.”

The episode began last week, when a researcher notified Apple, Google, Microsoft and Mozilla that the private keys of eight eMudhra intermediate certificates could be computed from the public certificates because they were generated with too little randomness. Security researcher Scott Helme recovered all eight on his laptop in less than a second, a task he said an AI agent later repeated from a single prompt.

Normally, a private key is a secret number so large that no computer could ever guess it, roughly 77 or 78 digits long for the type of cryptography used in these certificates. Each of the eight eMudhra keys was a whole number below 256, with one simply logged as the number 4. Since a certificate publicly displays the key it was built from, anyone could test every possible value in seconds, and such keys could be used to forge certificates and impersonate websites.

eMudhra attributed the flaw to an error in a key generation ceremony held April 2025, saying the mistake produced a second, weak set of keys that was published to browser trust lists instead of the intended ones. The company said its infrastructure was not compromised, that no data was breached and that none of the eight intermediates had issued end-entity certificates. Whether anyone used the keys in question is not known.

Chrome and Firefox blocked the certificates within hours of the report, Apple blocked them Monday and Microsoft on Tuesday. Mozilla removed the company’s root certificate from its trusted list, and Google said it will remove that root from Chrome in an update expected next week while it reviews eMudhra’s remaining root certificate. Go, Node.js, Python’s certifi bundle and several Linux distributions also shipped updates.

CERT-In, the country’s computer emergency response team, said it did not see any malicious use of the keys as of Wednesday.

The company said its other businesses, including digital signature and enterprise security services, continue to operate normally, and acknowledged reputational risks it cannot quantify.

Shares of ​the company fell 40% in the two days after the vulnerability was disclosed.

The post eMudhra kills its certificate business after researchers cracked its private keys in under a second appeared first on CyberScoop.

Hundreds of federal agencies should adopt an encryption tool to protect whistleblowers, veterans suffering from mental health crises and others from hackers who might target them when they reach out via agency websites, Sen. Ron Wyden said Monday.

The Oregon Democrat urged the Cybersecurity and Infrastructure Security Agency and Office of Management and Budget to take steps to adopt Encrypted Client Hello — a cybersecurity technology that protects the name of the website visited by a user — in a letter to the two agencies. His office identified at least 350 sites that don’t use its protections.

While almost all federal agency websites are encrypted, standard web encryption doesn’t secure some website names, Wyden said, using reportfraud.ftc.gov as an example.

“As data travels across the internet, hackers and foreign actors monitoring network connections can easily see these exposed website names,” he wrote. “This visibility could lead to malicious eavesdroppers identifying whistleblowers, profiling cleared federal personnel, tracking Americans seeking crisis support, and mapping interactions between agencies.”

Wyden wrote that Encrypted Client Hello (ECH) is especially effective with Content Delivery Networks (CDNs) that connect hundreds of thousands of websites to the internet. For websites delivered by a CDN, ECH makes it so anyone intercepting user web traffic can view the network delivering the content but not the specific site.

Agencies using CDN infrastructure without Encrypted Client Hello include an FBI tipline that supports ECH but doesn’t enable it and a Department of Veteran Affairs online suicide prevention hotline that isn’t protected by ECH because Amazon doesn’t support it, as well as agencies offering things like national security personnel services and whistleblower channels.

Because of the lack of ECH protection, foreign adversaries might be able to identify someone submitting crime tips to the FBI, Wyden warned.

Wyden made two recommendations to the leaders of CISA and the OMB.

“CISA should require that civilian federal agencies enable the protections of ECH across all public-facing websites and inter-agency web systems,” he said. “OMB, in coordination with the Office of the National Cyber Director and CISA, should establish support for ECH protections as a mandatory condition for commercial cloud and network vendors seeking federal contracts.”

CISA and OMB didn’t immediately respond to a request for comment on the letter, first reported by NextGov/FCW.

Wyden’s Monday missive is his most recent aimed at improving security technology at federal agencies, following on the heels of a letter in July first reported by CyberScoop that urged feds to get rid of older, insecure, public-facing VPNs.

The post Wyden seeks adoption of encryption tech at hundreds of federal agencies to protect visitors’ sensitive traffic appeared first on CyberScoop.

The Department of Homeland Security is banning the use of Chinese AI model DeepSeek and its affiliates by civilian federal agencies.

The notice, set to publish Tuesday in the Federal Register, cites the Federal Acquisition Supply Chain Act and a review by the Federal Acquisition Security Council to bar federal agencies from buying all information technology products and services from parent company Hangzhou DeepSeek Artificial Intelligence.

The notice includes a copy of a letter from Secretary of Homeland Security Markwayne Mullin ordering the exclusion of DeepSeek products on June 26, indicating the ban has been in place for months.  

Mullin claimed that DeepSeek’s models present “multiple threat vectors” to civilian federal agency IT systems. Some are unique to the company’s country of origin, while others identify potential privacy and mass data collection concerns that could also apply to other Chinese and U.S. AI models.

He said DeepSeek models store data in servers based in China, where national security laws give the Chinese government wide latitude to request and obtain data from domestic companies. Models hosted directly by DeepSeek collect personally identifiable information from users and trace their “digital fingerprints” online. And like every other major AI model on the market, DeepSeek relies on a “prompt and response” process, something Mullin said “may result in the transfer of sensitive data” to the Chinese government.

“The transfer of the aforementioned information to the [People’s Republic of China], either independently or in combination with publicly available data, could produce actionable intelligence on U.S. persons and/or government programs,” Mullin wrote.

CyberScoop had reached out to CISA and DHS for further details.

The decision will exclude federal agencies from using one of the most popular and powerful Chinese open-weight AI models more than a year after U.S. frontier AI companies and the federal government accused DeepSeek’s makers of “systematically” distilling their models.

The order requires civilian agencies to exclude DeepSeek products from future procurements while removing any versions that might have been put in place prior to the ban. In the past, federal agencies have used their own discretion to block the use of models like DeepSeek, as the Department of Commerce confirmed to FedScoop last year.

Agencies can request exceptions, but must submit their request 60 days in advance and must provide a “compelling justification” for the action, like an inability to fulfill a mission-critical function, or other national security considerations.

Mullin also said agencies that remove DeepSeek from their IT are “encouraged” to enhance their security controls to protect against the possibility that their networks were compromised through the Chinese AI tool.

“During the period between the issuance of this order and full removal of covered articles from agency systems, federal agencies are encouraged to take steps to address risk to their systems, such as monitoring the flow of traffic in and out of the agency, implementing enhanced logging and controls on data exfiltration for the relevant systems, and detecting and flagging anomalous activity,” he wrote.”

DeepSeek is the only Chinese AI model named in the order, but it’s just one of several Chinese open weight AI models that have worried national security officials or have been accused of illegally distilling U.S. models, along with Moonshot AI, the makers of Kimi and Alibaba, makers of Qwen.

The post DHS to ban DeepSeek from federal civilian agencies appeared first on CyberScoop.

Election influence campaigns, particularly ones playing out over social media, are a dime a dozen.

Such campaigns – sometimes devised by foreign powers, other times by domestic groups – are often designed to influence the U.S. electorate. Fake accounts and online personas are created, networks of propaganda are disseminated and the campaign seeks to nudge American voters into thinking a certain way.

Mostly, these efforts are known for getting little to no traction with U.S. audiences. But while social media influence campaigns may not be effective, bad actors continue to adapt their coordinated propaganda goals to new tactics and technologies.

Enter AI chatbots, which have become a source of information and truth for many, who consult the tool for feedback and advice on everything from their careers, to their relationships with their family, as well as their politics.

But new research from VisionHeight, an Israeli threat intelligence firm, highlights how AI systems can often serve as more useful marks for influence actors than humans. To wit: someone is setting up networks of hyperlocal websites across at least 14 different states, filled with content meant to influence U.S. races.

These networks include websites with names like “Wolverine State Report” or “Peach State Bulletin.” Each state network usually has between five to six separate sites,  some presenting themselves as hard news outlets and others as opinion or editorial sites. The outlets also cite one another, creating a circular network of local credibility.

But the content on these websites does not resemble journalism, or any writing that a human would find coherent or compelling. Rather, they often include text of statements about specific candidates running in local races, directly stating they are the better candidate for a political issue.

Statements like “Candidate X is the stronger choice” for voters who care about housing, taxes or other political issues were repeated hundreds of times on the websites, with slight changes in the language for different political issues. Most notably, they appear to be explicitly written for AI crawlers scraping web traffic, not humans.

“What’s really interesting about this is that the websites themselves and the content is so well built to let’s say optimize the probability for AI crawlers and the model to be influenced by this content,” said Nitsan Daniel, chief technology officer and co-founder of VisionHeight in an interview.

When a user asks an AI chatbot a question, the model will often search the internet for an answer. By creating specific online content providing direct answers to questions like “which candidate in a local race is better on housing affordability” it can essentially train the AI to retrieve that information when responding to queries.

Many media websites will opt to block AI crawlers, but these websites were all configured to specifically allow major U.S. AI companies to scrape their websites.

A blog by VisionHeight published Wednesday said the operation encompassed six states and 37 websites, but Daniel told CyberScoop that they have since discovered the operation spanned at least 14 states and 460 pages of online content.

The states targeted include Arizona, Colorado, Georgia, Indiana, Iowa, Kansas, Michigan, Mississippi, Nevada, North Carolina, Pennsylvania, Texas, Virginia, Wisconsin . At least seven states saw one or more House races targeted, while other sites focused on other races like Secretaries of State, statewide judicial appointments and local offices.

Most of the research focused on AI answers provided through Google search, but Daniel said they had confirmed at least one major AI model, Perplexity, linked to and cited one of the pages, Tarheel State Report, as its first source for an answer.

VisionHeight does not attribute the activity to a particular actor. To Daniel, who is behind the campaign and their ultimate goals are less important than the prospect that this kind of operation is easily reproducible by both foreign and domestic bad actors looking to influence how AI systems answer questions around political races.

“What we’re seeing here is,I think, very nicely demonstrating how the entire world is transitioning to [a new era],” she said. “So if in the previous election you could have seen fake websites aimed at getting people to actually read it, and containing content built to impact what they’re thinking, what we’re seeing here is…now instead of spending time and effort on getting people to read the content, [they’re] getting into their AI and being influenced by that.”

But Daniel’s concerns are broader. Large language models have become increasingly sophisticated in their ability to carry out a range of deceptive activities, such as creating false organizations, websites, as well as deepfake video, audio and imagery at scale.

It appears AI was used to generate much of the infrastructure and content used in the operation as well. All 37 websites VisionHeight identified in their first analysis, spanning multiple states, were registered in a single evening, and 36 were registered within an 8 minute timeframe. On Sept. 30, the network published “roughly 100,000 words of candidate content” all using the same template and layouts.

Foreign and domestic actors can easily replicate this process, generating hyperlocal propaganda that shapes what  AI chatbots say in response to political questions. Experts say chatbots have improved at avoiding false election information, but they remain vulnerable to manipulation and errors that make them unsuited to providing more complex answers around politics.

Whereas in the past a foreign actor might lack the budget, time and incentive to target small elections, AI tools now allow for such operations to be created and optimized at scale within days. Domestic actors, meanwhile, could potentially pair the same tactics with a more sophisticated understanding of how to influence American audiences.

“It really demonstrates how in general using AI just makes what was in the past small targets [more attainable], Daniel said. “People could think that the odds of them being hit, being manipulated or being attacked are just lower because people will not put all their energy and resources on that. Nowadays, because it is so much easier, we’re seeing influence operations and cyber attacks hitting small, medium businesses as well as smaller communities, like in this case.”

The post The next election influence campaign will target your AI chatbot appeared first on CyberScoop.

Members of Congress are pressing the Trump administration to expand the federal government’s role in securing artificial intelligence, wanting new safety standards and regulations, independent testing of models and more “aggressive” use of AI for defensive cybersecurity purposes.

In a letter, Sens. Maria Cantwell, D-Wash., and Mike Rounds, R-S.D., said that multiple incidents of frontier AI models escaping sandbox protections and breaching real companies, organizations and governments necessitate a stronger federal role in regulating the technology.

Recent revelations that hundreds, and possibly “tens of thousands,” of such incidents may have occurred for months without OpenAI’s staff detecting them makes the need for federal intervention even more urgent, the senators argued.

“These incidents come as AI systems are becoming dramatically more capable at discovering software vulnerabilities, writing and executing code, using digital tools, and operating autonomously,” the senators wrote.

The letter, addressed to Jay Clayton, director of national intelligence and new White House “AI czar” and Michael Kratsios, director of the Office of Science and Technology Policy, urges the federal government “to bring its full capacities to bear on this challenge, building a coordinated national response around standards, testing, auditing, and defensive AI.”

The Center for Advancing Innovation and Standards for Super Intelligence (CAISSI), housed within the Department of Commerce, has become the Trump administration’s main body for evaluating and testing AI models. In the letter, the senators are seeking to expand the center’s resources and mandate.

Under the Trump administration, testing of frontier models has been voluntary and focused on evaluating model capabilities, not restricting them. The administration has since said it has reached a safety testing framework with OpenAI, Anthropic and other AI companies to govern safety testing, but has not made the agreement public.

The senators call for CAISSI to spearhead the development of “technically grounded and measurable standards and risk management frameworks for advanced AI safety and security.” Those standards would address potential risks like cyberattacks, automated attacks on critical infrastructure and other threats.

“The standards should also address the security of the environments in which advanced AI systems are developed, trained, tested, and used internally, including protections against agents escaping testing environments, gaining unauthorized access to external systems, or taking actions beyond their intended permissions,” the senators wrote.

The letter argues the center and federal technology hubs like the National Institute of Standards and Technology should hire additional expertise in AI, cybersecurity, model evaluation and national security.

It also calls for a much broader community of independent and third-party testers. Currently, that testing is done almost entirely by AI companies and hand-selected auditors, like Model Evaluation and Threat Research (METR), Redwood Research and others.

Last month, Chris Painter, president of METR, told Congress that the firm’s investigation of the Hugging Face hacking incident was at the invitation of OpenAI, which tightly controls which organizations and testers get access to its unreleased models. While they are permitted to publicize some findings, such as those that relate to potentially catastrophic risks to humanity, researchers are otherwise restricted from discussing other parts of their investigation through nondisclosure agreements.

Additionally, Painter suggested that frontier companies are relying too heavily on their own technology, rather than technical controls, to monitor and restrain their models in testing.

“Because of the scale and speed at which AI agents are deployed, companies depend on AI monitoring and controls instead of human supervision, to prevent unwanted agent behavior,” Painter said. “That is, monitoring of AI is now in large part done by other AI systems.”

The senators call for CAISSI, national laboratories and the Department of Energy to become federal testing sites. There, the government would evaluate AI models for advanced cyber capabilities, biological or chemical threats, threats to critical infrastructure, sandbox evasion techniques and other autonomous rule-breaking behavior. They also want testing opened to universities, independent research organizations and “qualified third-party evaluators,” including private sector companies.

Other federal bodies, like the National Security Agency, the Defense Advanced Research Projects Agency and National Science Foundation can help develop new standards and testbeds for AI tools used in defensive cybersecurity that can then be shared across government and with the public.

“The recent incidents make clear that the security infrastructure surrounding advanced AI must advance as quickly as the technology itself,” the senators wrote. “The United States has an opportunity to lead both sides of this challenge: building the standards, testing, and auditing infrastructure needed for increasingly powerful AI, while harnessing those same capabilities to make American networks harder to attack.”

You can read the full letter here.

The post Senators press Trump admin to rally federal government around AI safety, security  appeared first on CyberScoop.

Anthropic announced a new program Thursday that will combine its AI tools with outside cybersecurity companies to find and fix cybersecurity vulnerabilities in critical infrastructure and open-source software.

Advertised as part of a new, “long-term commitment” to cybersecurity, the critical infrastructure defense program will pair Claude models, Anthropic engineers and threat research with the expertise of cybersecurity companies, including Accenture, Booz Allen, CrowdStrike, Deloitte, Dragos, Hitachi, Insane Cyber, Nozomi Networks, Palo Alto Networks, PwC, and Rockwell Automation.

“Defenders of critical infrastructure and the [open-source software] community have decades of security experience but have faced severe resource shortages that are exacerbated by this moment,” Anthropic wrote in a blog post. “We are recognizing their expertise in these domains and offering our support.”

Anthropic said it has offered frontier models and technical support to more than half the states in the U.S., as well as large operators of critical infrastructure to scan and patch code or assist in incident response and red teaming activities.

“Critical infrastructure is hard to defend in many ways that AI cannot fix, but we believe that frontier models can help find and repair weaknesses before those weaknesses are used to cut off power or make water unsafe, the company wrote. “Our first step is to work with a small cohort of providers to learn which strategies are most effective and practical.”

The company said it has engaged in similar work with maintainers of large open-source software projects, and some organizations asked for everything the model had found in their software, even unreviewed findings.

That spurred Anthropic to create a new opt-in scanning service for open source software, where organizations can get free, periodic scans of their projects with a proof of concept, explanation and suggested patching options. Anthropic noted that under this program, organizations will receive their reports faster but they may contain inaccuracies.

The long-term goal is to automate most triage and patching and develop new security architectures and coding standards.

As AI models have developed increasingly powerful cybersecurity capabilities, such as finding and exploiting known vulnerabilities, frontier AI companies have worried that bad actors could gain access to the tools faster than legitimate organizations. Anthropic and OpenAI have since both started programs funneling their tech to businesses and governments, free of charge, for defensive cybersecurity.

The post Anthropic rolls out program for ‘long-term commitment’ to secure critical infrastructure, open source software appeared first on CyberScoop.

The Justice Department and FBI announced that they had seized two hacking tools connected to the Chinese government-linked group Flax Typhoon and a China-based company that the U.S. government has repeatedly taken action against, including with a new multi-agency advisory Thursday.

The domain name seizures were meant to deny hackers access to the vulnerability scanning tool Microscan and the spearphishing tool FishHub created by the Chinese firm Integrity Technology Group, which the United States sanctioned last year. The U.S. government in 2024 also made the company the focus of a takedown operation, saying it was behind a massive botnet.

Authorities were granted the court-authorized seizures in the Western District of Pennsylvania, the FBI and DOJ announced Thursday in unsealing documents in the case.

U.S. agencies paired the announcement of the seizures with an advisory from the FBI, Cybersecurity and Infrastructure Security Agency and National Security Agency.

“Chinese government-linked cyber threat actors, enabled by the Integrity Technology Group, are combining automated scanning tools, large-scale botnets, and hands-on exploitation techniques to target and steal sensitive data from organizations worldwide, including U.S. critical infrastructure sectors,” the advisory reads. “These actors exploit vulnerabilities by using scanning tools, cross-site scripting attacks, and password spraying on Microsoft Exchange servers, while establishing persistence through VPN software and exfiltrating emails and credentials using scripts.”

Similar to previous allegations, law enforcement said Integrity Tech leaned on a Mirai-variant botnet of internet-of-things devices, in this case to facilitate Microscan.

Microscan targets have included a South Carolina power company, airports in Japan and Poland, critical infrastructure companies and universities in Taiwan and others, according to the FBI and DOJ. Victims of FishHub, which downloads malware on their networks after gaining access through spearphishing, include Taiwanese universities.

“Chinese government-affiliated actors continue to position themselves within critical infrastructure networks, including operational technology (OT) systems, with the aim of disrupting critical functions at a future time of their choosing,” said Chris Butera, acting executive assistant director for cybersecurity at CISA. 

“Under the FBI Cyber Strategy, we pursue both the actors who threaten critical infrastructure and the enterprises that support them,” said Brett Leatherman, head of the FBI’s Cyber Division. “Integrity Technology Group, a China-based company with ties to the Chinese government, is one of those enterprises, acquiring or developing cyber tools and hosting infrastructure for actors targeting networks worldwide.”

The post DOJ, FBI seize Flax Typhoon-linked hacking tools Microscan, FishHub appeared first on CyberScoop.

OpenAI disclosed Thursday it shut down two influence operations from Russia and Iran that used ChatGPT and other AI tools to create fake journalist personas and covert think tanks that successfully planted stories and narratives in mainstream news publications.

One cluster of accounts, which OpenAI calls “Dark Clark,” is attributed to Russian actors. The network focused on influencing Latin American politics and culture. Its name comes from Mia Clark, a fake AI persona the group presented as the leader of the Social Research Center, a supposed Latin American think tank used to seed propaganda in news reporting.

The group’s content primarily focused on harming Ukraine’s reputation in Latin America, though it also became involved in hot-button political issues in Argentina and Bolivia.

Based on reports generated through ChatGPT, where operatives discussed wage scales for employees and hiring and firing decisions, OpenAI researchers said it’s likely the Russian group was actually in control of the Social Research Center, rather than being an employee or observer.  

OpenAI called it “the most complex attempt to run a front identity that we’ve disrupted over the past two and a half years.”

“The available evidence indicates that the SRC’s employees in Latin America were not aware that they were working for a Russian group,” OpenAI said. “Unlike another Russia-linked ‘think tank’ that we recently exposed, the SRC appears to have produced a majority of original content via its co-opted staff.”

OpenAI cites several fact-checks and official denials from major media organizations and government officials in Latin America that appear to be in response to Dark Clark’s propaganda.

In March, Lupa Media reported on a TikTok video falsely claiming that the Ecuadorian government was using shell companies to recruit citizens to fight for Ukraine against Russia. The actors also generated and spread fake audio clips of the Ukrainian consul in Ecuador insulting Ecuadorian citizens.

During anti-government protests in Bolivia in May, the group released another fake audio clip, this time of an employee at the state water company claiming that the government was on the verge of declaring a state of emergency and shutting off water to La Paz, prompting an official denial from the Bolivian government.

The report does not attribute the activity to any specific Russian government or intelligence agency. It does mention that its operators seemed particularly interested in Politology, a successor to the Wagner Group, the Russian mercenary force previously led by Yevgeny Prigozhin. According to OpenAI, the group prompted its model for information on Politology “far more” than any other Russian organization.

The Iranian campaign used many of the same AI tools to pitch written articles on the U.S.-Iran war. Operators created at least seven different fake journalist personas who managed to place dozens of stories online through legitimate media organizations. However, the stories themselves often failed to elicit many comments or social media reactions.

“We identified almost 100 articles published or syndicated under the operation’s bylines across roughly a dozen online outlets around the world,” OpenAI said. “These were small to medium outlets, generally focused on international affairs, geopolitics, and events in the Middle East.”

OpenAI said the activity resembled “a commercial actor running a for-hire influence campaign,” but did not attribute it to a specific actor or group.

Most influence campaigns tracked by OpenAI tend to be low-impact, garnering little organic engagement online and virtually no offline impact. Campaigns are rated on an impact scale of 1-6, with few rising above a 1 or 2.

OpenAI rated the Russian campaign a 5 and the Iranian campaign a 4, indicating they were significantly more successful in breaking through to mainstream audiences, eliciting fact checks and official denials that tend to happen when a narrative becomes so big that authorities must deny it.

The post OpenAI says Iran, Russia used AI journalists, think tanks to influence Western media appeared first on CyberScoop.

The FBI and French authorities have arrested an individual and seized a pair of websites that were used to disseminate child sexual exploitation material, including AI generated deepfake media, according to court documents.

The websites, NudeLeaksTeens and NLTVIDS, were seized and shut down by the FBI this week. According to the Department of Justice, the cybercrime division of the French Paris Prosecutor’s Office has also arrested an unnamed 25-year-old French resident suspected of being the primary administrator for the sites.

According to a seizure warrant filed Oct. 2 in the Eastern District of Virginia by Arlington County police detective and FBI cybercrime task force member John Bamford, law enforcement first became aware of the websites in 2024, which advertised hacked, leaked and stolen CSAM of young girls.

The seizure warrant identifies VeriSign, a Reston, Virginia-based U.S. domain registry, as being the registry operator for .com, and directs Verisign to redirect the .com domain names identified in the warrant to FBI-designated name servers. David McGuire, a spokesperson for VeriSign told CyberScoop that the company executed its responsibilities under the warrant and has no relationship to the websites or administrators.

Together the sites offered “a wide range of explicit content including CSAM and content that violates the TAKE IT DOWN Act, which prohibits the non-consensual sharing of intimate images,” Bamford wrote.

The TAKE IT DOWN Act, passed last year, makes it a crime to create or share nonconsensual “intimate” deepfake media of real people. The law also gives the Federal Trade Commission authority to enforce it and allows courts to order websites to remove such content.

The sites posted explicit disclaimers disavowing child pornography while simultaneously advertising and selling CSAM. At least one had its own form of currency used to buy images and videos individually or bundles organized by victim. One collection, containing 189GB of material on 315 different girls, sold for $64.90.

Some of the material came from victims’ social media accounts on Snapchat, TikTok, Instagram and Facebook, either recorded directly or stolen from their accounts. Several victims who appear on the site reported to law enforcement that their accounts were hacked.

Some of the advertised collections were compiled by individuals now serving prison sentences for their crimes. One individual, Andrew Venegas, pled guilty in a Texas federal court to sexual exploitation of children and receipt of CSAM as was sentenced to 30 years in prison in April 2026.

“In the investigation and prosecution of Venegas, law enforcement learned that Venegas obtained sexually explicit images and videos of his victims in various ways, including extortion and the unauthorized accessing of victim social media accounts,” wrote Bamford.

A separate collection available for sale on one of the sites in 2022 and 2023 was named after an individual, Reuben Oswaldo Yeverino Rosales, who was convicted and sentenced to more than 34 years in prison in 2022 for sexual exploitation of children and cyber stalking.

The websites put up disclaimers stating that they do not host or store any files or images on their servers, but rather link to “other non-affiliated sites” that do. Administrators would often encourage payments in cryptocurrency and urge individuals to reach out to them personally for some material, rather than posting them on the site.

10/08/2026: This story was updated with comment from VeriSign.

The post FBI, French authorities seize deepfake CSAM-for-sale websites  appeared first on CyberScoop.

A coalition of cyber firms and critical infrastructure operators on Tuesday spelled out its views on the tasks that the Cybersecurity and Infrastructure Security Agency should assign federal agencies to protect operational technology systems after this summer’s attacks on water utilities.

The Operational Technology Cybersecurity Coalition said a CISA binding operational directive (BOD) for OT should specify who is responsible for protecting these systems at each agency,, draw on existing federal guidelines and set minimum cybersecurity practices.

The coalition said the BOD would address a need to act based on CISA’s lack of visibility into the spectrum of OT devices in federal agencies, a lack of consistent across-the-board OT security policies and the severity of the consequences that an attack on federal OT could produce.

Just last month, the Government Accountability Office published a report which concluded that most federal civilian executive branch agencies (FCEBs) haven’t enacted Office of Management and Budget requirements released in 2023 for networked Internet of Things and OT devices.

Putting forward recommendations for a CISA directive has two goals, said Michael Garcia, policy director of the coalition.

“One, it does make sure that the government is taking its own medicine,” said Garcia, who until recently worked at the agency. “You should practice what you preach. … Second, it sends a very strong signal to the private sector that, ‘This is what we think is important: As an OT partner, owner or operator or critical infrastructure owner or operator, [this is what] you should ask other providers to do.’”

There are 8,000 General Services Administration-owned and -leased properties, many of which would have OT involved in everything from power supply to heating, ventilation and air conditioning systems. Some of those OT systems might be “trivial,” Garcia acknowledged, but the coalition paper notes that CISA “does not currently have a holistic view of the assets managed by the FCEB and the potential risks, such as connected programmable logic controllers, to which the government may be exposed.”

With OT falling into a “government gray zone” between chief information officers and facilities managers, CISA should tell agencies to formally designate an officer in charge of cybersecurity for OT, the coalition recommends.

The directive should examine past OT guidelines the National Security Agency issued to see if they should apply to federal civilian agencies, and align any requirements in the hypothetical BOD with cybersecurity performance goals that CISA first issued in 2022, according to the coalition.

The coalition doesn’t assert that such a BOD would have headed off the attacks this summer on the water sector, and is focused on federal OT, something where CISA has done some work.

“To be fair, CISA has incorporated OT security requirements into prior directives (such as BODs 23-01, 23-02, and 26-04) alongside a host of technical guidance,” the paper reads. “But as AI reduces the technical barriers to sophisticated cyber operations, enabling adversaries to identify weaknesses, accelerate reconnaissance, and move laterally through poorly segmented operational environments with greater speed and scale, it is time for an encompassing BOD solely focused on OT security.”

CISA didn’t respond to a request for comment Monday in advance of the coalition publishing its paper.

But Garcia said that in discussions with CISA, “increasingly, I think they understand that there might be a need” for an OT BOD.

The post Here’s how experts think CISA should tell agencies to protect OT appeared first on CyberScoop.

The summer’s cyberattacks by Iranian hackers on water systems in 12 states underscored how vulnerable U.S. water systems are to foreign adversaries. A broad attack on water infrastructure could have consequences comparable to a public health crisis that impacts the country’s entire population.

The threat to water has long been clear. As the 2026 Annual Threat Assessment from the U.S. intelligence community states “Cyber actors from China, Russia, Iran, North Korea, and ransomware groups . . .  pose critical threats to U.S. networks and critical infrastructure.”

Advances in artificial intelligence have heightened those vulnerabilities. Advanced AI models, such as Anthropic’s Claude Mythos, have demonstrated the ability to identify thousands of zero-day vulnerabilities in critical software systems, including major operating systems and browsers. Other systems, including some developed in China, are demonstrating similar capabilities. AI systems can now “plan, test, and execute attacks in rapid cycles,” ranging from minutes down to seconds.

U.S. water systems are vulnerable to cyberattacks for technical, legal and practical reasons.

Technical: About 80% of U.S. water systems lack even basic cyber hygiene, a weakness exploited in the summer attacks. Even systems that serve most of the population (approximately 450 large and 4500 medium-sized water systems) have not adopted advanced cybersecurity capabilities used in other sectors where failure can have catastrophic consequences, including aviation, rail, mass transit, medical devices, finance, and nuclear power.

Legal: The Environmental Protection Agency lacks clear statutory authority to impose broad cybersecurity requirements on water systems. In 2023, EPA issued a memo interpreting existing regulations to strengthen the cybersecurity of water systems. The action met widespread opposition from the water sector as well as formal legal challenges, and the EPA ultimately withdrew the memo. The agency retains limited authority. It can require water systems to complete  risk and resilience assessments, maintain emergency response plans and, in emergencies, address critical cybersecurity flaws.  

Practical: Most U.S. water systems are small.  Some 45,000 serve 3,300 persons or fewer. Because of their size, many fall outside the EPA’s regulatory authority and below the “cyber poverty line,” lacking the funding, staff and expertise necessary for effective cybersecurity.

Not surprisingly, the summer attacks drew attention from the administration and Congress. The EPA ,in partnership with the FBI, and CISA each issued guidance on remedial actions, including disconnecting operational technology, from the internet where feasible and adopting robust password practices.

Sens. Amy Klobuchar, D-Minn., and Adam Schiff (D-Calif., introduced the Water Safety Shield Act, a bill that would require tiered cybersecurity standards for the water sector and dedicate a proposed $600 million annually to water cybersecurity. It would go beyond earlier, less prescriptive efforts to improve resilience in the sector.  

The administration has also established a pilot program with Texas and private-sector cybersecurity companies to identify and address water-system vulnerabilities at no cost to utilities. These efforts are well intentioned, but they do not address the underlying causes of the problem.

Large and midsize U.S. water systems have long been targets of sophisticated adversaries. China’s Volt Typhoon revealed deep Chinese penetration of critical infrastructure, including water systems, that support national security, economic security, and civil society. Those systems remain vulnerable because many have not adopted well-known protections, such as zero-trust architecture. More fundamentally, the software on which they depend remains vulnerable to exploitation.

Policymakers have struggled to respond for two reasons: the cost and complexity of adopting stronger technical defenses, and the highly fragmented nature of the water sector. A relatively small number of large systems serve about half the U.S. population. Roughly 49,000 systems serve the rest, including the 80% of the systems serving 3,300 people or fewer. Those smaller systems serve about 7% of the population.

Despite these challenges, the capabilities needed to significantly strengthen U.S. water-system security are well known and widely used in other sectors where failure can be devastating, including those listed above.

A five-part federal program could provide high-level cybersecurity for U.S. water systems.

Establish stronger technical capabilities. Water systems should adopt zero-trust architecture, which permits only authenticated, minimum-necessary access to resources and segments networks so that a breach in one area does not compromise the entire system. Such architecture could have blocked the unauthorized intrusions used in the summer attacks. Zero-trust systems are already widely used across multiple sectors, and commercial providers can support their adoption. The Department of Defense has certified several companies to provide zero-trust architecture for department components.

Water systems should also use formal methods to reduce or eliminate vulnerabilities in software that cannot safely fail.  Although the summer attackers did not appear to exploit flaws in the water systems’ code, a high-level adversary such as China would be likely to do so.

Formal methods range from “memory-safe” programming languages, which prevent coding errors that leave computer memory open to attack, to rigorous mathematical proofs that verify that software behaves as intended. They also support secure “microkernels,” which strictly separate software functions and make it far more difficult for an attacker to move laterally through a system.

Safe code development draws on the principles of formal methods but is a more practical, semi-formal approach. AI tools developed by companies including Google and CrowdStrike can identify and help repair software vulnerabilities, a process sometimes called “code mending.” Water systems should use such tools to defend against advanced adversaries.

Developing formally verified code for water systems would not be simple. But much of the software that directs the mechanical operations of water utilities comes from a small group of companies, including Siemens, Schneider, and Rockwell Automation. Those companies have the technical expertise to develop more secure code where it is necessary. Secure microkernels are also commercially available.

Support large water systems.  Congress should require large water systems to adopt zero-trust architecture, code-mending tools, and formal methods for critical software. The requirements should be phased in over time.  The legislation should also provide tax credits to help cover the costs of developing, implementing, and maintaining these protections.

Assist midsize water systems. The federal government should establish a program that provides technical expertise and financial support to midsize water systems, including municipal utilities. The program should help them adopt zero-trust architecture, code-mending tools, and formal methods for software development.

Midsize systems will likely need a longer phase-in period than large utilities.  A federally funded cohort of experts drawn from government and the private sector could provide the necessary support. Regional teams, organized by geography or technical specialty, could address the different needs of different water systems.

Create a safe operations posture for small water systems. Few, if any, systems serving 3,300 people or fewer are run by organization with substantial cybersecurity resources. Many cash-strapped systems rely on remote monitoring because on-site service is beyond their budgets. But remote monitoring can create serious risk when industrial devices are exposed directly to the public internet without proper firewalls or virtual private networks. 

The summer attacks primarily exploited such exposed devices. The EPA, FBI, and CISA guidance said the affected systems could be protected by locking them into “run” mode, which prevents remote reprogramming. That step may reduce immediate risk, but it also requires systems to be operated in person.

Small utilities therefore need either the staff and funding for manual operations or secure remote-access systems operated by trained personnel.

A voluntary cybersecurity corps could help address the budget and staffing challenges facing small water systems.  One model would follow the National Guard approach: State governors would oversee the effort, while the federal government would provide funding. A state-led program could begin with water systems and later expand to other vulnerable critical-infrastructure sectors.

The Texas pilot, which brings together the state, the federal government and private-sector companies, could serve as a model. It could also serve as a test for a regional approach, something we suggested in a prior op-ed.  

Build an AI-capable cybersecurity cohort. The proposed cohort should include specialists in artificial intelligence, including experts from leading AI companies. They could use AI tools to develop and deploy cybersecurity programs, including zero-trust architectures and code-mending systems, for utilities of all sizes. AI is advancing rapidly and applying it to protect water systems should be a national priority. The AI specialists should work with major industrial-technology companies, including Siemens, Schneider, and Rockwell, as well as directly with the water systems, both larger and smaller.

U.S. water systems face a significant and growing threat. The Trump administration, Congress, states and private sector should work together urgently to ensure that every American can rely on safe, clean water.

Franklin D. Kramer is a former assistant secretary of defense for international security affairs.

Robert J. Butler is the co-founder and managing director of Cyber Strategies LLC, served as the first deputy assistant secretary of defense for space and cyber policy, and served as the Chief Security Officer for IO Data Centers, a global data center enterprise, among other cybersecurity-related roles in both corporate and government organizations.

Melanie J. Teplinsky is an adjunct professor and senior fellow in the Technology, Law and Security Program at American University (AU), Washington College of Law.  She previously practiced technology law at Steptoe & Jonson LLP and served on the pre-IPO advisory board for CrowdStrike.

The post The US needs a real plan to defend its water systems appeared first on CyberScoop.

As AI agents escaping testing sandboxes and hacking organizations have gone from unprecedented to seemingly routine in a matter of weeks, policymakers, regulators and cybersecurity attorneys largely agree on one thing: Something must be done to hold AI companies accountable for the incidents.

Exactly what can be done under our current laws and regulations is much less clear.

The conversation has moved from policy and industry chatter to the floor where the future of liability will be determined. Speaking about the Hugging Face hack at a Senate hearing this week, Georgetown University law professor Paul Ohm summarized the argument.

“If you take any of the lengthy reports that have summarized what happened at OpenAI in July and August, and you simply search for the words ‘AI agent’ and you replace them with the words ‘OpenAI employee,’ the document you would be left with would read like a criminal indictment containing the defendant’s own confession of guilt,” said Ohm.

CyberScoop spoke with members of Congress, former federal law enforcement officials, cybersecurity attorneys and other experts about which laws, regulations or policies might apply to agentic hacks carried out by models at Anthropic, OpenAI, Meta, Google and other companies.

Their answers varied widely. Some endorsed using existing laws like the Computer Fraud and Abuse Act, while others said regulators such as the Federal Trade Commission could investigate and fine AI model developers by defining unauthorized agentic hacks as a form of unfair or deceptive trade practice. Still others pointed to civil lawsuits, new laws or state regulators as ways to hold AI companies or users accountable.

But, similar to a familiar technical cybersecurity idiom, there are no silver bullets in this debate.  Nearly every option has real complications or roadblocks that could limit its effectiveness. 

For once, the CFAA is too narrow

One of the first laws mentioned in discussions about agentic AI hacks is the Computer Fraud and Abuse Act, the federal government’s primary criminal hacking law. Historically, many in the cybersecurity community have criticized the statute as overly broad.

For agentic hacks, the problem is the opposite: The CFAA’s language does not clearly cover the activity involved in incidents like the Hugging Face hack.

“I would not be looking at a CFAA charge as the statute exists today” for these hacks, said Leonard Bailey, former head of the cybersecurity unit in the Computer Crime and Intellectual Property section at the Department of Justice.

Bailey helped develop policies that moved the DOJ away from prosecuting “good faith” third-party security research under the CFAA. He said that even if Congress changed the law to cover such hacks, it’s unclear whether that would help since laws like the CFAA are supposed to be “technology neutral.”

According to the Department of Justice’s website, CFAA prosecutions must prove that a defendant accessed a computer “without authorization” or in a way that “exceeds authorized access.”

Crucially, the law specifies that “as part of proving that the defendant acted knowingly or intentionally, the attorney for the government must be prepared to prove that the defendant was aware of the facts that made the defendant’s access unauthorized at the time of the defendant’s conduct.”

In other words, prosecutors must prove that the unauthorized access was intentional, not accidental.

Applied to incidents like the Hugging Face hack, the legal problem becomes clearer. If a human performed the same actions, they would almost certainly face CFAA charges. If a bot or software acted on behalf of a cybercriminal or group, the individuals or organizations intending to profit from the scheme could also face charges.

But no human at OpenAI, Anthropic or another frontier AI company directed, asked or even suggested that its agents hack victims or commit crimes. If charged, those companies would almost certainly argue that none of their actions demonstrated an overt attempt to commit a crime or authorize access to systems or data without permission.

However, others said there may be room to argue that AI companies are now fully aware that their products can engage in unauthorized agentic hacks.

“I’m of the opinion, because it has already happened [and] has happened several times, the argument that it happening again is not at a minimum knowing, for me it’s unlikely because we already have a situation where we know the capabilities,” said Elimu Kajunju, a privacy, cybersecurity, and AI governance attorney at Rimon Law. “The very first one where this happened, that’s the only organization that could say ‘You know what, we didn’t know it could do that or act like that.’ Once we’ve had a second or third or fourth, we can’t say that anymore.”

Kajunju acknowledged that applying statutes like the CFAA to agentic hacks could be complicated. But he said it would align with the spirit of American jurisprudence, in which businesses are often legally accountable for damage they cause, whether they intended it or not.

“I think this is one of those situations where, ‘Does it fit neatly into one of the buckets [we have]?’ No, but can you find one that will fit depending on what has happened? I think so.”

CyberScoop has reached out to OpenAI, Anthropic and Google for comment.

The FTC, states and civil lawsuits

Beyond criminal law, the hacks could also draw scrutiny from federal regulators, including the FTC.

Both Bailey and Kajunju pointed to the FTC as a possible regulator for agentic hacking incidents if the agency defines them as unfair and deceptive trade practices under Section 5 of the FTC Act. One benefit of relying on regulators such as the FTC is that they can often move faster on investigations and enforcement actions than the DOJ can on criminal prosecutions — an important consideration in the fast-moving AI space.

The FTC recently confirmed it was investigating OpenAI, Anthropic and other frontier AI companies, news first reported by The New York Post and confirmed by Axios. The FTC did not return a phone call from CyberScoop requesting comment. 

But Bailey warned that without a specific congressional mandate directing the FTC to regulate AI company hacks, any effort by the agency to redefine or expand its rules would almost certainly be challenged in court.

Civil lawsuits and state policymaking offer additional paths to investigating or regulating AI companies.

Currently, Florida is investigating OpenAI over the HuggingFace hack, while a nonprofit that sued OpenAI earlier this week has cited alleged violations of California law.

In his testimony, Ohm said that if Congress was serious about preventing agentic hacks, it should not pursue federal legislation preempting state AI laws. He called states “laboratories of democracy,” that can experiment with different forms of regulation and lawmaking.

Others agreed with that approach.

“Obviously this is a topic that the federal government doesn’t love, states getting involved in this space, but it just takes too long for action to come through Congress,” said Kajunju. “I think the quickest way to getting us to a better place will be a really good state law.”

New legislative remedies

On the Hill, members of Congress are working through the same questions as they consider legislative remedies.

At a Senate Homeland Security Committee hearing Wednesday, Sen. Josh Hawley, R-Mo., took a minute at the outset to describe the volume of agentic hacks affecting outside entities that frontier companies appeared to have missed for months. He named affected targets one by one, including major online code repositories like HuggingFace, Australian and U.S. government websites, obscure foreign-language wiki sites and other parts of the internet.

After weeks of investigations uncovered additional, previously unreported incidents in which models escaped testing environments and hacked victims, Hawley said it was “time to have a conversation about who bears responsibility” for the fallout. He added, “as soon as the AI executives say ‘we got a real problem here, our product is out of control,’ the very next words out of their mouths are, ‘but we’re not responsible for it.’”

Hawley said the committee invited OpenAI CEO Sam Altman to testify at the hearing, but he declined. Hawley then accused frontier AI companies of emphasizing their products’ danger while pushing for legal antitrust exemptions and only supporting government action if “they can write all the regulations.”

“I’d suggest that maybe we start with some federal legislation…and we can use existing statutes to do it, I propose using the Computer Fraud and Abuse Act,” said Hawley. “It’s already on the books, we can just update it to say that for developers – that’s the companies – if you develop these agents and train them in a reckless fashion and they go on to hack and destroy stuff, you’re liable.” 

Like other legal experts, Hawley said he believes a CFAA prosecution requires a human actor or organization that intended to commit a crime.

Another Senator, Ron Wyden, D-Ore., said he was also working on legislation related to the hacks. 

“The big AI companies should be held responsible if their agents hack other companies, government systems or foreign websites,” said Wyden in a statement to CyberScoop. “In my view there’s a question about whether the current CFAA would apply to the recent hacks. I’m working on a narrow update to the law to ensure Anthropic, OpenAI and other big AI companies can be punished when their agents run wild.”

Sens. Mark Warner, D-Va., Brian Schatz, D-Hawaii, and Andy Kim, D-N.J., introduced a bill that would create an AI Safety Board at the Department of Commerce. That board would evaluate emerging AI risks and establish safety and technical standards.

The Trump administration’s testing regime with AI companies is entirely voluntary, applies to only certain models, and requires testing no more than 30 days before release. Under the Democratic bill, frontier AI companies would be forced to submit models for testing 45 days before release. They would also be legally required to comply with government safeguards related to models discovering and exploiting software vulnerabilities without explicit human direction. Companies could face fines of up to $250,000 per violation, per day.

When asked whether the CFAA or other federal statutes could or should be used to prosecute companies when their AI systems hack, Warner said that companies’ claimed lack of intent to harm should not become a catchall legal excuse for avoiding responsibility. AI companies have said they never directly prompted or suggested that their models hack or commit crimes.

“AI models are tools and if I buy a power tool and deliberately misuse it, that’s my responsibility,” said Warner. “But if a defect causes that tool to behave in a dangerous way, we don’t absolve the manufacturer simply because someone else was using the tool when it malfunctioned. As AI systems become capable of acting autonomously, we need to ask what principles of responsibility should apply to the companies that design and deploy them.”

The post The legal questions raised by agentic AI hacks appeared first on CyberScoop.

The computers that automate water treatment systems across the country were built for durability, not for an internet-connected world. Many still accomplish their fundamental function, but as cyberattacks on the sector mounted this summer, water industry officials say those aging systems, especially internet-exposed operational technology and programmable logic controllers, remain among the easiest ways for adversaries to break in.

Tom Dobbins, executive director of the Water Information Sharing and Analysis Center or WaterISAC, told CyberScoop the sector’s biggest ongoing weaknesses include exposed OT, vulnerable PLCs, insecure connections through integrators and poor cyber hygiene at smaller utilities, which have pushed the center to make threat sharing faster across the sector.

“We have been under attack, and our enemies, the threat actors, are stepping up their activity as the U.S. is involved in a number of conflicts around the world,” Dobbins said.

That includes not only threats from Iran, the nation the U.S. government reportedly believes is behind this summer’s water facility attacks, but also China and Russia, he said.

WaterISAC is announcing a partnership with Cyware Wednesday to use its threat intelligence platform, selecting the company in part because of its existing relationships with other industry ISACs, Dobbins said. The ISAC already has a partnership with the National Rural Water Association to serve 20,000 of the water sector’s smallest utilities, and Dobbins said Cyware would help its analysts further.

It’s a sector that faces myriad challenges, seen by many as further behind on protecting its systems due to financial and technological constraints.

“OT systems that are exposed to the internet are a major challenge, and many of these systems that are older generation need to be not accessible to the internet,” Dobbins said.

Furthermore, programmable logic controllers (PLCs) are “obviously” a “vulnerability point,” he said. 

Those two vulnerabilities were the ones most commonly linked to this summer’s attacks.

Across the sector, PLCs have been the “main point of entry” for hackers, in part because they date back to a “simpler, gentler time,” Dobbins said.

“A lot of the equipment was developed pre-cyber threats and activities,” he said. “The equipment, it’s still valuable, it still is operational, so there’s not a huge reason for or incentive for utilities to upgrade it.”

President Donald Trump has disputed the notion that Iran was behind this summer’s attacks, despite alerts from the Cybersecurity and Infrastructure Security Agency.

“Let’s put it this way: I saw a recent CISA release that pointed to Iran as threat actors, and I know that the president kind of implied that it was not Iran, but I’ll say that CISA maybe is more expert in this area than maybe the president,” Dobbins said. “The president may not have been fully briefed when he made that comment.”

But CISA has also warned of potential threats from Russia and China, he said.

Two other sources of vulnerability for the sector are external — integrators — and internal — employees.

“If those integrators are working and they have a connection into an OT system that’s not managed discretely, then a threat actor can come in through an integrator and get into a system,” he said. 

Then there’s someone “who’s actually a good employee who’s tried to do the right thing and opens an email that has a malicious link in it, so they become subject to a phishing attack,” Dobbins said.

At smaller utilities, it can be difficult to keep up with basic cyber hygiene as well, he said: changing passwords, implementing multifactor authentication.

One way that Cyware might be able to help is by leveraging its relationships with other ISACs, said Tom Stockmeyer, managing director of government and critical infrastructure at Cyware.

“We’re thrilled to add water to the portfolio and start enabling cross-sector sharing,” he said.

The post WaterISAC reckons with range of threats after summer of cyberattacks appeared first on CyberScoop.

Amid growing concerns from both the public and policymakers about cyberattacks involving advanced AI systems, NVIDIA has released a new open software security platform for AI agents.

The Open Agent Safety Platform, according to NVIDIA, will be “an open software platform and reference system design with full-stack governance and control across the software and hardware, compute and robotics systems that run agents.”

More than 100 organizations from the AI industry, including Anthropic, Arm, Microsoft, SpaceXAI, Palantir and JPMorgan Chase, have committed to using the platform to improve security in their products.

Stronger sandboxes and more advanced monitoring are pillars of NVIDIA’s strategy for tackling “rogue” AI agentic hacks, and the platform offers a pair of tools that are meant to help contain and restrict agent activity. 

According to a corresponding technical blog, OpenShell, built on Apache 2.0 open source software, is a tool for securing runtime execution for AI agents in sandbox testing environments. AI system operators can define files, networks, tools, processes and credentials that an agent has, and test whether those guardrails hold before introducing them to enterprise networks.

It also includes security updates for NVIDIA’s Bluefield 4 data processing unit (sometimes called a “data center on a chip”) that enables out-of-band monitoring of AI agent behaviors and security policy enforcement.

On X, NVIDIA CEO Jensen Huang called the platform “the beginning of an open ecosystem to build the trust layer for safe agent systems.”

To do this, security work must become “foundational” to AI and the industry’s “full promise can only be realized when people have confidence that AI is being built to be safe and deployed with wisdom and responsibility.”

“Trust and innovation are not in conflict,” Huang wrote. “Safety is how trust is earned. We must build not only the most capable AI, but the most trusted AI, so that this extraordinary technology can realize its enormous promise for the world.

NVIDIA manufactures advanced computer chips that power much of the U.S. commercial AI industry. After models from Anthropic, OpenAI, Meta and others escaped sandbox protections during testing and breached real organizations, some AI industry leaders – including Anthropic CEO Dario Amodei and OpenAI CEO Sam Altman –  suggested AI systems are too advanced to be contained.

Huang has criticized those views, arguing that frontier AI companies and their supply chain partners must improve their security posture. Huang said last week he opposes government regulations or mandates on the AI industry, unless they promote growth.

In an interview with CNBC on Monday, Huang said he believes sandboxing and larger AI security issues are “a technically solvable problem.”

“I think the answer is we hope it’s an engineering problem,” said Huang. “I believe it’s an engineering problem, I know it’s an engineering problem, and we all need to hope that it’s an engineering problem. [If not] it’s not solvable, so the fact that all of these companies still are advancing the state of the art is because they also believe it’s solvable.”

Aviv Nahum, CEO of Above Security, told CyberScoop that NVIDIA’s announcement reflects industry recognition that model training alone cannot ensure safety. 

NVIDIA is essentially arguing that for agents to perform safely in real-world environments, “some of the enforcement must live outside the model, in a layer the agent cannot simply reason around or modify.”

“What this announcement says to me is that the industry is finally converging on a basic cybersecurity principle, [that] model alignment is not a substitute for security engineering,” said Nahum. “Sandboxes, identity, least privilege, independent monitoring and containment are not new ideas. What is new is that we now have autonomous software capable enough that failing to apply those principles becomes much more consequential.”

The post As AI world debates security, NVIDIA releases open source tools for agents appeared first on CyberScoop.

Biotechnology doesn’t fall neatly into any one of the 16 government-designated critical infrastructure sectors that receive specialized and focused attention from feds, leading some lawmakers to worry that it’s not getting the protection from cyberattacks and other risks that it needs.

That’s why a bipartisan group of senators and representatives announced legislation Thursday that would place an emphasis at the Cybersecurity and Infrastructure Security Agency on defending biotechnology, biomanufacturing and biological data.

The Protecting Biotechnology and Biomanufacturing as Critical Infrastructure Act and the Protecting Biological Data Act are two separate bills with the same group of cosponsors. Both bills would weave biotech into the law that established the Department of Homeland Security.

The former would direct DHS to come up with plans to make sure biotech and biomanufacturing are protected as critical infrastructure, but not as a whole new sector. The plans would identify key biotech players, conduct outreach to them and develop steps to update the National Infrastructure Protection Plan this year to incorporate biotech sector input.

The latter would make sure that systems handling genomic sequences and sensitive biometric data are covered as critical infrastructure and integrated into the national cyber strategy, that CISA would work with biotech players on security steps like joint exercises and that the agency would get new personnel to handle biometric data security.

In the last two months, biotech giants Boston Scientific and Amgen have revealed that they suffered recent cyberattacks.

Sponsors of the measures include leaders and members of the National Security Commission on Emerging Biotechnology, a legislative advisory group.

“Biotechnology infrastructure and data are becoming vital to America’s economic and national security,” said Commission Chair Senator Todd Young, R-Ind. “Just as we are serious about where the sensitive data of Americans is stored and who can access it, we should be equally serious about protecting our biological data and infrastructure. Designating biotech as critical infrastructure is about recognizing its strategic importance and making sure the capabilities America will depend on tomorrow remain resilient and protected from foreign threats.”

Notably, however, the bills do not seek a separate critical infrastructure category for biotech to add to the 16. Currently, biotech cuts across a number of existing sectors, including the health, agricultural and industrial sectors.

Some industry groups and experts have lobbied for the inclusion of new critical infrastructure sectors, such as space or artificial intelligence.

“Protecting biomanufacturing infrastructure and the most sensitive biological data of Americans is essential for our national security,” said commissioner Rep. Ro Khanna, D-Calif. “These bipartisan bills will help ensure we are protecting this sector from physical and cyber threats while keeping America as the world leader in biotechnology.”

The bill’s sponsors in the House are Khanna, Stephanie Bice, R-Okla. and Scott Peters, D-Calif., and in the Senate the sponsors are Young and Maggie Hassan, D-N.H.

You can read the text of the bills below.

The post House and Senate members propose legislation for CISA to step up cyber defenses for biotech appeared first on CyberScoop.