A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks

2020/05/20 by Yashar Deldjoo, Tommaso Di Noia, Deldjoo, Yashar +3 · 28 citations
Computer Science · #Adversarial Robustness in Machine Learning #Adversarial machine learning #Adversarial system #Artificial intelligence #Collaborative filtering #Computer science #Cryptography and Security (cs.CR) #Deep learning #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Generative adversarial network #Generative grammar #H.3.3 #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine learning #Multimedia (cs.MM) #Recommender system #cs.CR #cs.IR #cs.LG #cs.MM

paper · pdf · doi:10.48550/arxiv.2005.10322

published in arXiv (Cornell University) (Cornell University) · 37 pages, submitted to journal

openalex publication_date 2020/05/20 · arxiv created 2020/11/10 · arxiv updated 2020/11/11 · openalex created_date 2020/11/23 · openalex updated_date 2026/07/28

Abstract

Latent-factor models (LFM) based on collaborative filtering (CF), such as matrix factorization (MF) and deep CF methods, are widely used in modern recommender systems (RS) due to their excellent performance and recommendation accuracy. However, success has been accompanied with a major new arising challenge: many applications of machine learning (ML) are adversarial in nature. In recent years, it has been shown that these methods are vulnerable to adversarial examples, i.e., subtle but non-random perturbations designed to force recommendation models to produce erroneous outputs. The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions. In this survey, we provide an exhaustive literature review of 74 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality.

Citations

• Generative Adversarial Networks
• Distilling the Knowledge in a Neural Network
• Matrix Factorization Techniques for Recommender Systems
• Poisoning Attacks against Support Vector Machines
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Improved Techniques for Training GANs
• Categorical Reparameterization with Gumbel-Softmax
• Conditional Image Synthesis With Auxiliary Classifier GANs
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets
• Domain-to-Domain Translation Model for Recommender System
• On Evaluating Adversarial Robustness
• Compatibility Family Learning for Item Recommendation and Generation
• A Survey of Adversarial Learning on Graphs
• Multi-Step Adversarial Perturbations on Recommender Systems Embeddings
• An Empirical Study of DNNs Robustification Inefficacy in Protecting Visual Recommenders

Related

• Security Matters: A Survey on Adversarial Machine Learning
• Defenses in Adversarial Machine Learning: A Survey
• A Comprehensive Review of Adversarial Attacks on Machine Learning
• Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey
• Trustworthy Machine Learning under Social and Adversarial Data Sources