Meta has joined a growing list of companies saying their models hacked into an external company’s system during cybersecurity testing.
In a statement on Thursday, the social media company said its Muse Spark model “exploited a security vulnerability in a third-party service, in a manner similar to previously-reported instances with other companies.”
The Meta spokesperson said the breach occurred because of a misconfiguration by Irregular, an independent company Meta uses for model testing. This led to the model accessing the internet during evaluation.
Meta added that it learned of the incident when Irregular notified the company. It says it is investigating the incident and plans to issue a full retrospective once the company has all the details.
The Information first reported on the Meta AI model incident on Wednesday. Irregular did not immediately respond to a request for comment from Business Insider.
Meta is the third AI giant to report such a rogue agent breach in the last few weeks.
Late last month, open-source AI platform Hugging Face said that it had experienced a cybersecurity breach in which an AI agent had accessed some of its systems. OpenAI disclosed that two of its models escaped a test environment and were responsible for the rogue hack.
On Wednesday, OpenAI self-reported two more security lapses, in addition to the Hugging Face hacking incident. The AI lab said that the incidents occurred while external parties were testing the model’s capabilities.
Last week, Anthropic disclosed a similar incident, saying that it found three cases of Claude models gaining unauthorized access to other companies’ systems.
These hacking incidents have prompted calls for more AI safety regulation and reporting.
In an interview with CBS that aired on Sunday, Hugging Face CEO Clem Delangue called for mandatory disclosures of AI cyberattacks. Transparency can help everyone learn about and prevent attacks, he said.
“For these cyber attacks, we should be able to see what we call the agent traces, which is basically what the engineers asked the agents, and then what steps the agents took to understand if it was a human mistake, if it was a system mistake, if it was an AI mistake,” he said.
In response to the first OpenAI incident, Aaron Levie, the CEO of Box, said the attack was an example of the “wild times” we are headed toward with AI.
“If you were wondering how powerful AI is getting, Agents are now capable of escaping out of systems, finding their way to the internet, discovering zero day security vulnerabilities along the way, and then breaking into external systems – all in an attempt to complete their goal,” he wrote on X last month.
