Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures
Thanh Toan Nguyen, Quoc Viet Hung Nguyen, Thanh Tam Nguyen, Thanh, Trung Huynh, Thanh Thi Nguyen, Matthias Weidlich, Hongzhi Yin

TL;DR
This survey comprehensively reviews poisoning attacks on recommender systems and evaluates countermeasures, providing a taxonomy and analysis to aid in protecting these systems from malicious data manipulations.
Contribution
It introduces a novel taxonomy for poisoning attacks, organizes over 30 attack types, and evaluates more than 40 countermeasures, filling a gap in systematic understanding.
Findings
Provides a detailed taxonomy of poisoning attacks
Evaluates effectiveness of various countermeasures
Highlights open issues and future research directions
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpam and Phishing Detection
MethodsFocus
