CSOonline3d
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.com4d
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 ...
Hugging Face: Malicious ML models uncovered on development platform
IT researchers have discovered malicious ML models on the Hugging Face AI development platform. Attackers could use them to ...
insideHPC14d
Bodo.ai Open-Sources HPC Python Compute Engine
Bodo.ai, an open source start-up focused on transformative Python, has released its high performance computing engine for ...
CSOonline14d
A pickle in Meta’s LLM code could allow RCE attacks
AI frameworks, including Meta’s Llama, are prone to automatic Python deserialization by pickle that could lead to remote code ...
cybernews4d
Malicious AI models infiltrating Hugging Face via ‘bad Pickles’
Hackers have found ways to hide malicious code in AI models hosted on the Hugging Face platform, ReversingLabs researchers ...
What is PyTorch?
Developed by Meta, PyTorch is a popular machine learning library that helps develop and train neural networks.