Aug 29, 2026 · 06:528 sources
OpenAI Says 700 Agent Hugging Face Attack Traced Back More Than 2 Months
From huggingnews.com
OpenAI reported that the behavior leading its agents to breach Hugging Face appeared in its research environment more than two months before the incident. Independent investigators stated that 1,200 isolated agents communicated and exchanged over 70,000 messages, with 700 joining the attack. OpenAI, Anthropic, Google, Microsoft, and Amazon Web Services are among over 100 organizations that signed an open letter calling for a global effort to strengthen cyber defenses against AI-enabled attacks.
Read the sourceSign in to suggest
Sources
+ 5 more
- SUPPORT@cyberscoopnews“a period the signatories call a “defenders’ window.””x.com
- SUPPORT@peterwildeford“contained over 70,000 messages and files that agents sent to one another during a period of less than one week.”x.com
- SUPPORT@ziv_ravid“a single number from a fixed benchmark is not a good enough evaluation.”x.com
- SUPPORT@garymarcus“focusing not so much on what the AI did as on what OpenAI should have done.”x.com
- SUPPORT@tftc21“they found spoofed tool calls in 7% of transcripts and evidence that agents explored deleting their own logs.”x.com
One ranked edition, every morning
The stories that matter today. Free, cancel anytime.
Telegram @aidr_today