Collaboration with industry is key to balancing AI security risks and benefits, as well as staying ahead of China and other adversarial nations, National Cyber Director Sean Cairncross said Thursday.

The Trump administration is facing pressure from some quarters of Capitol Hill and even some artificial intelligence executives to establish regulations or embrace legislation to guard against the technology’s risks, something the president himself has rejected.

“We’ve never faced a world where our adversaries have the frontier in this space, and so our attempts to optimize that innovation and security is is something that is ongoing, but is increasingly efficient, and it depends on our relationship with industry and our ability to work collaboratively among the the interagency,” Cairncross said at the AI Edge event hosted by The Washington Post.

That collaboration is ever-increasing, he said, such as with the National Institute of Standards and Technology’s Center for Advancing Innovation and Standards for Super Intelligence (CAISSI).

“Industry coordination on this, across critical infrastructure sectors, is improving both on industry-to-government and within industry,” he said. “There is collaboration with CAISSI and others as well to do evaluation and testing on these models. That includes work on guardrailing, sandboxing, et cetera.”

But “we’ve seen in the past, once the government is introduced into this space directly, there is a tendency for the government to start to want to adjust the dials directly, and it is difficult to reverse that,” he said. “I think that would slow, at this point, the innovation cycle that is to our benefit.”

One of the things that has increased the calls for stronger government action is when OpenAI acknowledged that its AI agents went outside testing to hack Hugging Face in July.

“Since that incident,” Cairncross said, “the engineering work that’s gone into improving systems awareness of that has increased by an order of magnitude.”

But the AI companies need to secure themselves against China for the United States to stay in the lead, he said.

“Both on the hardware side and on the computer science side and engineering, we’re in the lead. I think our lead is significant,” Cairncross said. “The Chinese have designed a sort of fast follow that relies quite a bit on distillation efforts … And I think industry is increasingly aware of this: that their systems are secure, that the technology, as it’s being developed, is protected.”

Other administration officials have called out China for allegedly using distillation to train its models. In July, Michael Kratsios, who leads the White House Office of Science and Technology Policy, claimed that Moonshot AI, a Beijing, China-based AI company, had distilled Anthropic’s recently released Fable model to develop its own K3 model.

On Wednesday, OpenAI said clusters of activity tied to Moonshot AI were part of a “coordinated” distillation campaign.

Cairncross said earlier this week that the U.S. government is collaborating with industry to integrate AI into critical infrastructure for security purposes. 

Cairncross said the Trump administration wants to make sure national security systems do the same. One of his office’s pilot programs is with the Defense Department and the Cybersecurity and Infrastructure Security Agency “that touches on the defense infrastructure in particular,” in addition to a pilot on rural hospitals.

The post National cyber director: Government-industry collaboration vital to managing AI risks, competition with nations appeared first on CyberScoop.

OpenAI said it disrupted a “coordinated campaign” to distill and extract reasoning capabilities from its AI models, pointing the finger at a Chinese rival.

On Wednesday, OpenAI said it first spotted low-level activity on July 1 that gradually increased until July 24 and 25, when it observed 16,000 prompts from 4,000 users that fit a similar “relevant extraction pattern.” The number of suspicious users had climbed to 15,000 by July 28, when OpenAI said it “fully disrupted” the operation.

The company called the attackers’ method “novel.” They copied encrypted reasoning data from one conversation, then asked the model in a separate conversation to decrypt the content and transcribe it in plain text. Outside researchers reported a similar vulnerability to OpenAI in August.

“The operators did not break our encryption, compromise a database, or gain direct access to stored user conversations,” OpenAI wrote in an unsigned blog post. “Instead, they manipulated model interactions so that protected reasoning could be reproduced in forms visible to the requester in a coordinated, scaled manner that violated our terms of service.”

OpenAI said it’s unclear whether all the activity is related, but individuals working on behalf of Moonshot AI, a China-based rival AI company that has, in the past, been accused of distilling U.S. models, were behind a “core cluster” of the activity.

OpenAI’s blog post does not cite any technical evidence or reasoning for its attribution. Moonshot AI’s Kimi is one of several Chinese open-source AI models that are offering users and organizations good-enough performance for free or at a low cost.

American AI companies and the U.S. government have accused Chinese companies like Moonshot AI of conducting “systematic” distillation attacks on their latest models. Cybersecurity experts at Google and other cybersecurity firms say Chinese companies rely on black or gray markets to acquire thousands of individual accounts for models like Claude and ChatGPT. They then flood those models with millions of prompts and data requests that help them copy model capabilities and training data.

OpenAI told CyberScoop that it was not sharing any additional information “for security reasons.” CyberScoop has reached out to Moonshot AI for further comment.

According to OpenAI, the same vulnerability exists in other AI models, and it has shared information about the incident with groups like the Frontier Model Forum.

Beyond banning offending accounts, OpenAI said it improved signup and infrastructure controls and expanded network monitoring. It also fixed a bug that allowed users to take encrypted data from one conversation and decrypt it in another. 

The post OpenAI reveals ‘novel’ encryption bypass used in distillation attack  appeared first on CyberScoop.