Knowledge-enhanced Black-box Attacks for Recommendations

Abstract

Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles (i.e., a set of items that fake users have interacted with) into a target recommender system to achieve malicious purposes, such as promote or demote a set of target items. Due to the security and privacy concerns, it is more practical to perform adversarial attacks under the black-box setting, where the architecture/parameters and training data of target systems cannot be easily accessed by attackers. However, generating high-quality fake user profiles under black-box setting is rather challenging with limited resources to target systems. To address this challenge, in this work, we introduce a novel strategy by leveraging items' attribute information (i.e., items' knowledge graph), which can be publicly accessible and provide rich auxiliary knowledge to enhance the generation of fake user profiles. More specifically, we propose a knowledge graph-enhanced black-box attacking framework (KGAttack) to effectively learn attacking policies through deep reinforcement learning techniques, in which knowledge graph is seamlessly integrated into hierarchical policy networks to generate fake user profiles for performing adversarial black-box attacks. Comprehensive experiments on various real-world datasets demonstrate the effectiveness of the proposed attacking framework under the black-box setting.

arXiv commentAccepted in the KDD'22

References in corpus (6)

• Neural Graph Collaborative Filtering
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• Poisoning Attacks to Graph-Based Recommender Systems
• Data Poisoning Attacks to Deep Learning Based Recommender Systems
• Attacking Recommender Systems with Augmented User Profiles
• Revisiting Adversarially Learned Injection Attacks Against Recommender Systems

Cited by in corpus (5)

• Recommender Systems in the Era of Large Language Models (LLMs)
• IMF: Interactive Multimodal Fusion Model for Link Prediction
• Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention
• CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
• Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System