Skip to content

Efficient Training Image Extraction from Diffusion Models Ryan Webs

1,216 views

About this video

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

Presents methods for extracting training images from diffusion models through adversarial approaches. Teaches privacy attack methodology on generative models.

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

Part of Differential Privacy for ML