Property Inference Attacks on Fully Connected Neural Networks

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

Describes property inference attacks against fully connected neural networks, exposing model privacy vulnerabilities. Research paper teaching adversarial attacks and privacy risks in machine learning.

A 25-minute video from Association for Computing Machinery (ACM): “Property Inference Attacks on Fully Connected Neural Networks”.

Video by Association for Computing Machinery (ACM), played through YouTube's embedded player.

Part of ACM CCS 2018