Sources

16 Total Sources

Irregular Says AI Models Breached 1 Real Database After Naming Error

Far Left11%
Left67%
Center22%
SecurityWeek3d ago
Irregular: AI Models Attacked Real Company Database Due to Naming Error
The Verge4d ago
OpenAI AI Agent Goes Rogue, Hacking Companies in Cybersecurity Test
orfme.org8d ago
The 'Hugging Face' Hack: Why Open AI Models Should Be a Defence Priority - ORF Middle East
edrm.net8d ago
When AI Agents Go Rogue, the Logs Become Evidence - EDRM
Reuters8d ago
EXCLUSIVE: Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week | Reuters
The Atlantic8d ago
OpenAI Models Collude, Hack Hugging Face After Breaking Internal Systems
BBC.com8d ago
First OpenAI, now Meta - why do AI hacks keep happening?
Ynetnews4d ago
Advanced AI Models Exploit Test Environments, Access Internet in Cybersecurity Evaluations
NOTUS6d ago
OpenAI Details Rogue AI Agent Hack of Hugging Face Platform
WIRED7d ago
OpenAI Responds to Rogue AI Agents Breaching Hugging Face During Security Test
Security Affairs8d ago
OpenAI AI models exploited zero-days to reach Hugging Face in benchmark test
dev.to8d ago
OpenAI Sandbox Escape: The Full Timeline of How a Model Hacked Hugging Face - DEV Community
Mashable8d ago
Hugging Face OpenAI hack: Agent went rogue, escaped and hacked everything in its path | Mashable
Instagram8d ago
Last week, OpenAI, Meta and Anthropic reported that their models had gone rogue during routine security testing, with all three companies tracing the incidents back to the same Israeli startup, Irregular. Rise
Cybersecurity Dive8d ago
Hackers abuse AI models to find new entry paths | Cybersecurity Dive
Facebook8d ago
Researchers found a way to make a weaker AI decode a stronger model's hidden reasoning. They extracted hidden traces from OpenAI, Anthropic, and Google APIs, recovering secret API keys and passwords,