BrighterTube

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training

Google TechTalks349K subscribers

About this video

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

Analyzes privacy effects from adding or removing personal information in LLM training, measuring information flow. Teaches sensitivity analysis for data's role in model behavior.

A 42-minute video from Google TechTalks: “Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training”.

Science & MathProgramming & CS

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

Part of Differential Privacy for ML