← Back to Feed
Adam Shostack Talks Hugging Face & PHANTOM-B
August 17, 2026 · Dark Reading · Severity: LOW
World-class threat modeler Adam Shostack shared he was "blown away" by OpenAI's revelations about the Hugging Face attack, and explains why his new threat model for LLMs is both "lightweight yet still usable."
Key Takeaways
- Adam Shostack shared he was blown away by OpenAI's revelations about the Hugging Face attack during a recent discussion.
- The world-class threat modeler explained why his new threat model for LLMs is lightweight yet still usable for practitioners.
- Shostack's approach aims to make AI security threat modeling accessible without sacrificing analytical rigor or completeness.