FedRecAttack: Model Poisoning Attack to Federated Recommendation

TL;DR

This paper introduces FedRecAttack, a novel model poisoning attack on federated recommendation systems that leverages public interactions to effectively increase target item exposure, revealing vulnerabilities in assumed secure FR models.

Contribution

The paper presents FedRecAttack, the first attack exploiting public interactions to compromise federated recommendation systems, demonstrating significant effectiveness with minimal malicious participation.

Findings

FedRecAttack achieves state-of-the-art attack effectiveness.

Even with 3% malicious users, attack remains highly effective.

Side effects of the attack are negligible.

Abstract

Federated Recommendation (FR) has received considerable popularity and attention in the past few years. In FR, for each user, its feature vector and interaction data are kept locally on its own client thus are private to others. Without the access to above information, most existing poisoning attacks against recommender systems or federated learning lose validity. Benifiting from this characteristic, FR is commonly considered fairly secured. However, we argue that there is still possible and necessary security improvement could be made in FR. To prove our opinion, in this paper we present FedRecAttack, a model poisoning attack to FR aiming to raise the exposure ratio of target items. In most recommendation scenarios, apart from private user-item interactions (e.g., clicks, watches and purchases), some interactions are public (e.g., likes, follows and comments). Motivated by this point, in FedRecAttack we make use of the public interactions to approximate users' feature vectors, thereby attacker can generate poisoned gradients accordingly and control malicious users to upload the poisoned gradients in a well-designed way. To evaluate the effectiveness and side effects of FedRecAttack, we conduct extensive experiments on three real-world datasets of different sizes from two completely different scenarios. Experimental results demonstrate that our proposed FedRecAttack achieves the state-of-the-art effectiveness while its side effects are negligible. Moreover, even with small proportion (3%) of malicious users and small proportion (1%) of public interactions, FedRecAttack remains highly effective, which reveals that FR is more vulnerable to attack than people commonly considered.