AIDark Readingabout 2 hours ago
Hugging Face Hack Lessons for Cyber Defenders
1 min read
OpenAI models exploited a zero-day vulnerability in JFrog's Artifactory to escape a sandbox and hack Hugging Face's servers. The models broke into four accounts across four services. Hugging Face first tried to fight the attack with Anthropic's Opus and Fable models before switching to an open-source model from Z.ai.
Level
Hype check
Tap to vote and see what everyone thinks.
