Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective

TL;DR

This paper investigates Byzantine robustness in federated recommendation systems with sparse aggregation, proposing new attack strategies that exploit the unique aggregation mechanism and demonstrating their effectiveness in compromising system security.

Contribution

It introduces the first analysis of Byzantine attacks tailored to sparse aggregation in federated recommendation, redefining robustness and designing effective attack methods.

Findings

Spattack can prevent convergence with few malicious clients.

Sparse aggregation vulnerabilities can be exploited by new attack strategies.

Existing defenses are ineffective against the proposed attacks.

Abstract

To preserve user privacy in recommender systems, federated recommendation (FR) based on federated learning (FL) emerges, keeping the personal data on the local client and updating a model collaboratively. Unlike FL, FR has a unique sparse aggregation mechanism, where the embedding of each item is updated by only partial clients, instead of full clients in a dense aggregation of general FL. Recently, as an essential principle of FL, model security has received increasing attention, especially for Byzantine attacks, where malicious clients can send arbitrary updates. The problem of exploring the Byzantine robustness of FR is particularly critical since in the domains applying FR, e.g., e-commerce, malicious clients can be injected easily by registering new accounts. However, existing Byzantine works neglect the unique sparse aggregation of FR, making them unsuitable for our problem. Thus, we make the first effort to investigate Byzantine attacks on FR from the perspective of sparse aggregation, which is non-trivial: it is not clear how to define Byzantine robustness under sparse aggregations and design Byzantine attacks under limited knowledge/capability. In this paper, we reformulate the Byzantine robustness under sparse aggregation by defining the aggregation for a single item as the smallest execution unit. Then we propose a family of effective attack strategies, named Spattack, which exploit the vulnerability in sparse aggregation and are categorized along the adversary's knowledge and capability. Extensive experimental results demonstrate that Spattack can effectively prevent convergence and even break down defenses under a few malicious clients, raising alarms for securing FR systems.