Nicholas Carlini: The security of LLMs

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

LLM security vulnerabilities and attack methods are covered by Carlini with technical depth. A 77-minute lecture teaches threat modeling and defensive techniques for language models.

A 77-minute video from UC Berkeley EECS: “Nicholas Carlini: The security of LLMs”.

Video by UC Berkeley EECS, played through YouTube's embedded player.

Part of Understanding Large Language Models: Foundations and Safety