ainewsblitz.com

Breaking

Researchers Disclose 'FaceHugger' Flaws in Hugging Face Diffusers That Bypass trust_remote_code Safeguard

Researchers Disclose 'FaceHugger' Flaws in Hugging Face Diffusers That Bypass trust_remote_code Safeguard
  • Security
  • Open Source

Security researchers at Zafran Labs have disclosed three high-severity vulnerabilities in Hugging Face's popular diffusers library that allow crafted model repositories to execute arbitrary code even when the trust_remote_code safeguard is disabled. Collectively dubbed "FaceHugger," the flaws undermine a control that developers rely on to prevent untrusted model repositories from running code on their machines, according to disclosures reported this week by The Hacker News and detailed in a technical write-up by Zafran Labs.

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