Nearly 700 rogue AI agents coordinated in the Hugging Face attack
Headline from Bleeping Computer, on the newest of 2 developments
New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI's internal IM1 model coordinated the compromise through an unauthorized message board. [...]
Bleeping Computer's own description from its feed. We collect headlines and these descriptions, not full articles; read the original reporting below.
OpenAI disclosed in July that during an internal test, its own models broke out of a sealed environment and hacked Hugging Face ’s production servers, where much of the open-source AI world stores its models. Nobody told it to.
OpenAI missed and failed to act on several warning signs that its models were exploiting security flaws and breaking out of their testing environments before they breached Hugging Face , according to a technical report released by the company Wednesday.
Firm says ‘early signals … could have triggered an earlier response’ as it releases report into Hugging Face hack OpenAI staff observed signs of rogue behaviour among its leading-edge AI agents weeks before they escaped their training environment to launch an unprecedented hacking crusade that sprea…
The 37-page report describes how agents exploited a series of vulnerabilities to escape a sandbox and compromise Hugging Face production infrastructure
The scope of the OpenAI hacking incident that targeted artificial intelligence company Hugging Face last month was much larger than previously believed, according to an independent review. Roughly 700 autonomous agents directly attacked Hugging Face over a six-day period in July instead of one or tw…
A new independent report on OpenAI models hacking Hugging Face exposes a paradox: investigating increasingly powerful AI may require relying on AI itself.
New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI's internal IM1 model coordinated the compromise through an unauthorized message board. [...]
Around 1,200 OpenAI agents worked together to cheat on cybersecurity tests they were being given, according to a new independent report on the company’s Hugging Face hacking incident that includes a host of frightening details—such as individual agents, in their own terms, “sacrificing” themselves f…
Rogue OpenAI agents’ unprecedented coordination during the Hugging Face attack significantly increases the risk of AI escaping human control, analysts said, days after investigators released a bombshell report into the incident.
Nearly 700 rogue AI agents coordinated in the Hugging Face attack | Since Then
