This is the Registration for the IEEE SPS Webinar on 14.12.2023.

9.11 - 3:00pm Western European Time (UTC+1) (09:00am US Eastern Coast and 10:00pm Chinese Time)
Ming Ding, Principal Research Scientist at Data61, CSIRO, in Sydney, NSW, Australia.

Fundamentals of Privacy-Preserving Federated Learning
Abstract: Federated learning (FL) is gaining popularity as a decentralized machine learning method. It safeguards client data from direct exposure to external threats. However, attackers can still steal information from shared FL models. To address this, we've created a privacy-preserving FL framework using differential privacy (DP). Additionally, we establish a convergence upper-bound for the proposed DP-FL framework, revealing the existence of an optimal number of communication rounds for best convergence with privacy protection.

Please enter your mail address in order to register. The mail address will only be stored for the delivery of additional information about the webinar. It will be deleted after the webinar is conducted.

mail adress