By Raphael Satter
WASHINGTON, July 21 (Reuters) – OpenAI said on Tuesday that some of its AI models went rogue during a security test and triggered a hack that compromised the infrastructure of AI startup Hugging Face last week.
In a blog post, OpenAI said it was testing the capabilities of some of its most advanced models in a controlled environment but that the program managed to escape containment, reach the internet, and break into Hugging Face to try to satisfy its testing goal.
The blog post said the breakout was “an unprecedented cyber incident, involving state-of-the-art cyber capabilities” and that the company was reinforcing its safeguards.
Hugging Face, a platform used to host open-source large language models and datasets, caused a stir in the cybersecurity community when it said in a blog post last week that it had been the target of a hack that “was different from anything we had handled before” in that “it was driven, end to end, by an autonomous AI agent system.”
In a post to X, Hugging Face cofounder Clement Delangue said the company suspected the hack “might have come from a frontier lab, given the sophistication of the agent. Turns out it did!” He added: “It’s quite mind-blowing that all of this happened autonomously!”
OpenAI’s disclosure that its advanced models were responsible for the breach, despite having placed them in what it described as “a highly isolated environment,” will likely intensify disquiet over the power and risk of frontier models.
The U.S. cyber defense agency CISA and the U.S. National Security Agency did not immediately return messages seeking comment.
Matt Suiche, an engineer at agentic AI cybersecurity company Tolmo, said the incident showed that AI systems were now as potent as elite cyber operators.
“Frontier models are closing the gap with state-of-the-art attackers,” Suiche said. He warned that the sorts of breaches outlined in OpenAI’s blog post were possible to carry out with technology that was available well beyond the walls of frontier research labs.
“This is what we’ve already seen internally, with our agents we already have results like this,” Suiche said. “We don’t even have to use the latest models.”
(Reporting by Anhata Rooprai in Bengaluru; Editing by Pooja Desai, Rod Nickel and Aurora Ellis)
Comments