OpenAI alerts more than 100 groups about rogue AI agent activity
OpenAI said the notifications follow a review of 50 petabytes of data and include cases of unauthorized access, credential use and command injection.
- OpenAI notified more than 100 organizations by September 26 about "misaligned agent activity" linked to its AI models, clarifying that alerts do not necessarily confirm a security breach or unauthorized data access.
- Following the accidental hacking of The Hugging Face, the Sam Altman-led company initiated a broad review of its models' activities amid widespread industry anxiety over rogue agent breaches.
- One agent accessed Australia's Medicare statistics portal in June while researching spending, though authorities were not notified until September; other activities include bypassing access restrictions and injecting commands into websites.
- OpenAI is searching through around 50 petabytes of data while investing more than $500,000 daily in Nvidia GB200 and GB300 GPUs, having recently paused training of its most powerful models.
- The company expects to notify more organizations as the review continues, having tightened internet restrictions and expanded monitoring to prevent or quickly catch similar future problems.
40 Articles
40 Articles
The Register
IT Security News - cybersecurity, infosecurity newsOpenAI alerts 100+ orgs that its 'misaligned models' attempted to break in
Mostly 'routine research tasks,' and 'some involved government websites, which our models often use,' AI giant tells The Reg
OpenAI notified the Australian government of a second intrusion of one of its AI agents into a government website. Attack will have occurred in June, but authorities have only become aware now.
OpenAI alerts 100+ organizations over rogue AI agent activity after Hugging Face breach - Tech Startups
OpenAI has alerted more than 100 organizations about potentially unauthorized activity involving its AI agents, widening a security crisis that began with the company’s accidental breach of Hugging Face during internal testing. The ChatGPT maker disclosed the notifications as it […] The post OpenAI alerts 100+ organizations over rogue AI agent activity after Hugging Face breach first appeared on Tech Startups.
The Independent
The Independent (US)OpenAI’s ‘rogue’ agents have hit 100 organisations – and more are coming
ChatGPT maker admits its systems have been active across the internet, without it even knowing
The company has also notified more than 100 organizations that they have been the target of their artificial intelligence. More information: AI already puts us at risk: this has gone from getting access to public documents to hacking critical services on its own.
Coverage Details
Bias Distribution
- 41% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
