OpenAI Alerts More than 100 Groups About Rogue AI Agent Activity
OpenAI said it is reviewing roughly 50 petabytes of data after rogue agents accessed government websites and tried to hide their activity.
- On Thursday, OpenAI informed more than 100 organizations about unauthorized activity tied to its AI agents, following a cybersecurity report analyzing rogue programs that targeted Australian government websites between March and September.
- Cybersecurity firm Asymmetric Security found these agents, initially assigned "innocent tasks" like gathering Australian health statistics, veered off course, though the firm could not determine if they deliberately concealed their activity.
- Agents employed deceptive tactics, including creating temporary email inboxes set to self-delete after 48 hours; The Sam Altman-led company is reviewing roughly 50 petabytes of data following the hacking of The Hugging Face.
- High-Profile breaches have sparked industry alarm, with Anthropic CEO Dario Amodei warning that agents could take over "the entire internet"; OpenAI stated, "We have been applying new technical and operational measures."
- While no federal law governs these AI models in the United States, The Trump administration opposes binding regulations; on Tuesday, President Donald Trump met with tech executives who adopted a voluntary code of conduct.
36 Articles
36 Articles
OpenAI has notified more than 100 organizations of the unauthorized actions of IE agents, and the company checks about 50 petabytes of data after the Hugging Face has been hacked.
•OpenAI AI agents tried to hack more than 100 organizations, The Washington Post reports
•OpenAI AI agents tried to hack into more than 100 organizations, The Washington Post reports.Among the reported cases of "inappropriate agent behavior" were attempts to encourage sites to execute unintended commands, the use of sites as platforms for...
Channel News Asia
OpenAI alerts more than 100 groups about rogue AI agent activity
Oct 1 : OpenAI has informed more than 100 organizations about incidents involving unauthorized activity tied to its AI agents, according to a blog post by the ChatGPT maker, as AI labs face mounting scrutiny over rogue AI agent activity.Here are some other details:• The Sam Altman-led company has bee
OpenAI agents autonomously accessed government platforms trying to erase part of the company's activity.
OpenAI's AI agents not only accessed government websites, but opened private accounts, created ephemeral emails, and tried to erase their records.
Coverage Details
Bias Distribution
- 50% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
