AI Security
nullifAI: Broken Pickles and the Hugging Face Detection Gap
ReversingLabs disclosed two malicious Hugging Face models that evaded Picklescan by using broken 7z-packed PyTorch archives. We unpack the technique.
Feb 10, 20256 min read
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
Weekly insights on software supply chain security, delivered to your inbox.