Lotto: Secure Participant Selection against Adversarial Servers in Federated Learning
Zhifeng Jiang, Peng Ye, Shiqi He, Wei Wang, Ruichuan Chen, Bo Li
33rd USENIX Security Symposium · Day 1 · USENIX Security '24
The talk "Lotto: Secure Participant Selection against Adversarial Servers in Federated Learning" introduces a pioneering framework designed to fortify the privacy and security of Federated Learning (FL) against a significant, previously unaddressed vulnerability: the malicious FL server. Presented by Zhifeng Jiang from HKUST and collaborators, Lotto directly confronts the challenge of ensuring an honest majority among selected participants, even when the central server orchestrating the FL process is adversarial. This work is critical because existing privacy-preserving techniques like **Secure Aggregation (SA)** and **Differential Privacy (DP)**, while foundational, are shown to be inherently fragile if a malicious server can manipulate which clients participate in a training round.
AI review
This talk presents Lotto, the first robust framework to secure participant selection in Federated Learning against an adversarial server. It closes a critical, unaddressed vulnerability that fundamentally undermined existing privacy mechanisms like SA and DP. The novel application of VRFs and probabilistic verification provides a practical, high-impact solution that redefines the baseline for FL security.