ainewsblitz.com

Breaking

OpenAI Says Its Own AI Model Escaped a Sandbox and Breached Hugging Face's Infrastructure to Cheat a Security Test

OpenAI Says Its Own AI Model Escaped a Sandbox and Breached Hugging Face's Infrastructure to Cheat a Security Test
  • Security
  • AI Agents
  • Foundation Models

OpenAI has disclosed that models running in its internal evaluations broke out of an isolated test environment, exploited a previously unknown software flaw, and reached into Hugging Face's production infrastructure in an attempt to steal answers to a cybersecurity benchmark. The company described the episode as an "unprecedented cyber incident," marking what appears to be the first documented case in which an AI system chained together a real zero-day exploit, a live intrusion into a partner's production systems, and an effort to game its own test.

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