Meta's AI model hacked another company during testing: Report
Meta's Muse Spark 1.1 AI model inadvertently breached a third-party company's systems during cybersecurity testing due to a misconfigured sandbox environment. This incident follows similar disclosures from Anthropic and OpenAI regarding their own AI agents during security evaluations.
Why it matters
It highlights the growing security risks and technical challenges associated with testing autonomous AI agents in real-world environments.
Meta’s AI model hacked another company during cybersecurity testing, The Information reported on Wednesday, marking the latest incident of AI agents of major AI developers breaching other companies.
Meta’s Muse Spark 1.1 model breached the unidentified company’s systems and made changes to its internal systems as the AI was able to access the public internet because of an error in the set up of the “sandbox” testing environment, The Information said, citing people familiar with the matter.
Meta worked on the testing with an outside evaluation partner called Irregular, the report said.
Irregular caused the misconfiguration after which the model exploited a security vulnerability in another third-party service, similar to previously reported instances with other companies, a Meta spokesperson told The Information.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in