Knowledge-enhanced Black-box Attacks for Recommendations
This work addresses a security vulnerability in deep neural network-based recommender systems, offering a practical black-box attack method that could impact system robustness and user trust, though it is incremental in leveraging existing knowledge graphs and reinforcement learning techniques.
The paper tackles the challenge of generating high-quality fake user profiles for adversarial attacks on recommender systems under black-box settings, and introduces a knowledge graph-enhanced framework (KGAttack) that effectively learns attacking policies using deep reinforcement learning, as demonstrated through comprehensive experiments on real-world datasets.
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.