Lotto: Secure Participant Selection against Adversarial Servers in Federated Learning

TL;DR

Lotto is a federated learning system that ensures secure participant selection against malicious servers by using verifiable randomness and approximation techniques, maintaining system integrity without trusted servers.

Contribution

Lotto introduces a novel secure participant selection framework in federated learning that counters adversarial server manipulation without relying on trusted authorities.

Findings

Lotto's selection algorithms effectively limit compromised participants.

Theoretical analysis confirms alignment with honest client proportions.

Experiments show low overhead and comparable accuracy to insecure methods.

Abstract

In Federated Learning (FL), common privacy-enhancing techniques, such as secure aggregation and distributed differential privacy, rely on the critical assumption of an honest majority among participants to withstand various attacks. In practice, however, servers are not always trusted, and an adversarial server can strategically select compromised clients to create a dishonest majority, thereby undermining the system's security guarantees. In this paper, we present Lotto, an FL system that addresses this fundamental, yet underexplored issue by providing secure participant selection against an adversarial server. Lotto supports two selection algorithms: random and informed. To ensure random selection without a trusted server, Lotto enables each client to autonomously determine their participation using verifiable randomness. For informed selection, which is more vulnerable to manipulation, Lotto approximates the algorithm by employing random selection within a refined client pool. Our theoretical analysis shows that Lotto effectively aligns the proportion of server-selected compromised participants with the base rate of dishonest clients in the population. Large-scale experiments further reveal that Lotto achieves time-to-accuracy performance comparable to that of insecure selection methods, indicating a low computational overhead for secure selection.