Revisiting Adversarially Learned Injection Attacks Against Recommender Systems

Abstract

Recommender systems play an important role in modern information and e-commerce applications. While increasing research is dedicated to improving the relevance and diversity of the recommendations, the potential risks of state-of-the-art recommendation models are under-explored, that is, these models could be subject to attacks from malicious third parties, through injecting fake user interactions to achieve their purposes. This paper revisits the adversarially-learned injection attack problem, where the injected fake user `behaviors' are learned locally by the attackers with their own model -- one that is potentially different from the model under attack, but shares similar properties to allow attack transfer. We found that most existing works in literature suffer from two major limitations: (1) they do not solve the optimization problem precisely, making the attack less harmful than it could be, (2) they assume perfect knowledge for the attack, causing the lack of understanding for realistic attack capabilities. We demonstrate that the exact solution for generating fake users as an optimization problem could lead to a much larger impact. Our experiments on a real-world dataset reveal important properties of the attack, including attack transferability and its limitations. These findings can inspire useful defensive methods against this possible existing attack.

Accepted at Recsys 20

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Explaining and Harnessing Adversarial Examples
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Adversarial Attacks on Neural Networks for Graph Data
• Security Evaluation of Pattern Classifiers under Attack
• Poisoning Attacks to Graph-Based Recommender Systems
• Meta-Learning with Implicit Gradients
• Bilevel Programming for Hyperparameter Optimization and Meta-Learning
• LambdaOpt: Learn to Regularize Recommender Models in Finer Levels

Cited by in corpus (8)

• Shilling Black-box Recommender Systems by Learning to Generate Fake User Profiles
• Knowledge-enhanced Black-box Attacks for Recommendations
• Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
• Adversarial Item Promotion: Vulnerabilities at the Core of Top-N Recommenders that Use Images to Address Cold Start
• Uplift Modeling for Target User Attacks on Recommender Systems
• Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
• Adversarial Text Rewriting for Text-aware Recommender Systems
• Ready for Emerging Threats to Recommender Systems? A Graph Convolution-based Generative Shilling Attack