Going Back and Beyond: Emerging (Old) Threats in LLM Privacy and Poisoning

492 views

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

Identifies emerging and historical privacy and poisoning threats to LLMs, cataloging specific attack vectors. Teaches threat landscape and defense considerations for large language models.

A 47-minute video from Google TechTalks: “Going Back and Beyond: Emerging (Old) Threats in LLM Privacy and Poisoning”.

Video by Google TechTalks, played through YouTube's embedded player.

Part of Differential Privacy for ML