Cyber Security Webinar by Rui Wang MSc - Privacy-preserving Byzantine-Robust Federated Learning
07 December 2021 12:00 till 12:45 - Location: Zoom meeting | Add to my calendar
Join Zoom Meeting
https://tudelft.zoom.us/j/93851661903?pwd=UzhXVlAxellBUDhRRXdyNWYyOGdlUT09
Meeting ID: 938 5166 1903
Passcode: 931813
Abstract
Privacy and Byzantine-robustness are two major concerns of federated learning (FL), but mitigating both threats simultaneously is highly challenging: privacy-preserving strategies prohibit access to individual model updates to avoid leakage, while Byzantine-robust methods require access for comprehensive mathematical analysis. Besides, most Byzantine-robust methods only work in the honest-majority setting.
In this webinar, I will introduce previous works about this topic and presents some expected experimental results about Privacy-preserving FL to resist > 1/2 Byzantine attacks.