A Hugging Face account belonging to the creators of the Kokoro AI model was compromised by researchers. The attackers used the hijacked account to distribute a malicious version of the Kokoro model, which, when executed, would exfiltrate sensitive information from users' systems. The security researchers who discovered the attack have since secured the account and removed the malicious model. AI
IMPACT Highlights the security risks associated with AI model repositories and the potential for malicious code distribution.
RANK_REASON Security incident involving a compromised account on a platform distributing an AI model.
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →