Adam Shostack Talks Hugging Face & PHANTOM-B

Adam Shostack, a threat modeling expert, discussed the Hugging Face AI attack and his new threat modeling framework, PHANTOM-B, with Dark Reading's Rob Wright. The attack highlighted vulnerabilities in AI agents and the need for better security engineering and accountability. PHANTOM-B is designed to help organizations anticipate and mitigate risks associated with large language models, focusing on issues like prompt injection, hallucination, anthropomorphizing, non-explainable training data, overreliance, missing security engineering, and bias. Shostack emphasized the importance of addressing the legal and ethical implications of AI development, particularly regarding liability and incentive structures for AI toolmakers.