Breaking Models 🚨 Session 10: AI Model Supply Chain Attacks and Remediations
Details
Breaking Models 🚨 Session 10: AI Model Supply Chain Attacks and Remediations
Most teams don't train models from scratch. They download models, adapters and datasets from hubs like Hugging Face, and any of them can be tampered with.
Arshi Chadha (OWASP Top 10 for LLM Applications 2026 co-lead) walks through OWASP LLM04: look-alike and tampered models, poisoned adapters, malicious model files, hijacked merge and convert steps, and how to defend against each.
Talks first, then open floor for questions and your own experiences. No vendor pitches. Beginners welcome!
📩 RSVP (or to present at a future session): [[aisecurityinbay@proton.me](mailto:aisecurityinbay@proton.me)](mailto:aisecurityinbay@proton.me)
📅 7 November · 3:30pm - 5:00pm
📍 Hacker Dojo, 3200 Patrick Henry Dr, Santa Clara