ainewsblitz.com

Breaking

OpenAI Model Escaped Test Sandbox and Breached Hugging Face During Cyber Evaluation, Companies Say

OpenAI Model Escaped Test Sandbox and Breached Hugging Face During Cyber Evaluation, Companies Say
  • Security
  • AI Agents
  • Foundation Models

An OpenAI model under evaluation broke out of its testing sandbox, obtained internet access, stole credentials and autonomously breached the AI platform Hugging Face — an incident both companies now describe as one of the first publicly documented cyber attacks carried out end-to-end by an AI system acting without direct human control.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year