Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures

TL;DR

This paper addresses poisoning attacks in recommender systems, a training-time threat where adversaries inject crafted data to bias outcomes. It proposes a five-dimension taxonomy to systematically classify both classic heuristic and AI-based attacks, and links these to more than 40 countermeasures spanning detection and prevention. By cataloging 30+ attacks and 43 defenses, it illuminates which defenses are effective against which attacks and where gaps remain. The study provides practical guidance for building robust, trustworthy recommender systems and highlights open research directions, supported by a public resource repository for reproducibility and future work.

Abstract

Recommender systems have become an integral part of online services to help users locate specific information in a sea of data. However, existing studies show that some recommender systems are vulnerable to poisoning attacks, particularly those that involve learning schemes. A poisoning attack is where an adversary injects carefully crafted data into the process of training a model, with the goal of manipulating the system's final recommendations. Based on recent advancements in artificial intelligence, such attacks have gained importance recently. While numerous countermeasures to poisoning attacks have been developed, they have not yet been systematically linked to the properties of the attacks. Consequently, assessing the respective risks and potential success of mitigation strategies is difficult, if not impossible. This survey aims to fill this gap by primarily focusing on poisoning attacks and their countermeasures. This is in contrast to prior surveys that mainly focus on attacks and their detection methods. Through an exhaustive literature review, we provide a novel taxonomy for poisoning attacks, formalise its dimensions, and accordingly organise 30+ attacks described in the literature. Further, we review 40+ countermeasures to detect and/or prevent poisoning attacks, evaluating their effectiveness against specific types of attacks. This comprehensive survey should serve as a point of reference for protecting recommender systems against poisoning attacks. The article concludes with a discussion on open issues in the field and impactful directions for future research. A rich repository of resources associated with poisoning attacks is available at https://github.com/tamlhp/awesome-recsys-poisoning.

Figures (5)

• Figure 1: Adversarial attacks vs. poisoning attacks
• Figure 2: The process of a typical poisoning attack
• Figure 3: Taxonomy of poisoning attacks on RecSys.
• Figure 4: Effective countermeasures against poisoning attacks.
• Figure 5: Poisoning attacks that are resilient against certain countermeasures.