The Hacker News1h
Malicious ML Models on Hugging Face Leverage Broken Pickle Format to Evade Detection
Researchers discovered two malicious ML models on Hugging Face exploiting “broken” pickle files to evade detection, bypassing ...
CSOonline5h
Attackers hide malicious code in Hugging Face AI model Pickle files
The popular Python Pickle serialization format, which is common for distributing AI models, offers ways for attackers to ...
Infosecurity-magazine.com18h
Malicious AI Models on Hugging Face Exploit Novel Attack Technique
The technique, called nullifAI, allows the models to bypass Hugging Face’s protective measures against malicious AI models ...
ByteDance Develops OmniHuman, an AI Framework That Can Generate Realistic Videos of Humans
The use of motion signals is a novel technique, which the company is calling omni-conditions training. With this, the AI model is trained on different modalities, including text, image, audio, and ...