Multi-agent Attacks for Black-box Social Recommendations

• URL: http://arxiv.org/abs/2311.07127v4
• Date: Mon, 16 Sep 2024 06:51:46 GMT
• Title: Multi-agent Attacks for Black-box Social Recommendations
• Authors: Shijie Wang, Wenqi Fan, Xiao-yong Wei, Xiaowei Mei, Shanru Lin, Qing Li,
• Abstract summary: Graph Neural Networks (GNNs) have been widely studied to model user-item interactions and user-user social relations simultaneously. These advanced recommender systems are highly vulnerable to adversarial attacks, in which attackers can inject well-designed fake user profiles. We propose a novel framework MultiAttack based on multi-agent reinforcement learning to coordinate the generation of cold-start item profiles and cross-community social relations.
• Score: 27.08879125224201
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rise of online social networks has facilitated the evolution of social recommender systems, which incorporate social relations to enhance users' decision-making process. With the great success of Graph Neural Networks (GNNs) in learning node representations, GNN-based social recommendations have been widely studied to model user-item interactions and user-user social relations simultaneously. Despite their great successes, recent studies have shown that these advanced recommender systems are highly vulnerable to adversarial attacks, in which attackers can inject well-designed fake user profiles to disrupt recommendation performances. While most existing studies mainly focus on argeted attacks to promote target items on vanilla recommender systems, untargeted attacks to degrade the overall prediction performance are less explored on social recommendations under a black-box scenario. To perform untargeted attacks on social recommender systems, attackers can construct malicious social relationships for fake users to enhance the attack performance. However, the coordination of social relations and item profiles is challenging for attacking black-box social recommendations. To address this limitation, we first conduct several preliminary studies to demonstrate the effectiveness of cross-community connections and cold-start items in degrading recommendations performance. Specifically, we propose a novel framework MultiAttack based on multi-agent reinforcement learning to coordinate the generation of cold-start item profiles and cross-community social relations for conducting untargeted attacks on black-box social recommendations. Comprehensive experiments on various real-world datasets demonstrate the effectiveness of our proposed attacking framework under the black-box setting.

Related papers

• Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias [64.73474454254105]
  Social recommendation models weave social interactions into their design to provide uniquely personalized recommendation results for users. Existing social recommendation models fail to address the issues of popularity bias and the redundancy of social information. We propose a Condition-Guided Social Recommendation Model (named CGSoRec) to mitigate the model's popularity bias.
  arXiv  Detail & Related papers  (2024-05-27T02:45:01Z)
• Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought [43.490918008927]
  We propose shadow-free MIAs that directly leverage a user's recommendations for membership inference. Our attack achieves far better attack accuracy with low false positive rates than baselines.
  arXiv  Detail & Related papers  (2024-05-11T13:52:22Z)
• Poisoning Federated Recommender Systems with Fake Users [48.70867241987739]
  Federated recommendation is a prominent use case within federated learning, yet it remains susceptible to various attacks. We introduce a novel fake user based poisoning attack named PoisonFRS to promote the attacker-chosen targeted item. Experiments on multiple real-world datasets demonstrate that PoisonFRS can effectively promote the attacker-chosen item to a large portion of genuine users.
  arXiv  Detail & Related papers  (2024-02-18T16:34:12Z)
• Securing Recommender System via Cooperative Training [78.97620275467733]
  We propose a general framework, Triple Cooperative Defense (TCD), which employs three cooperative models that mutually enhance data. Considering existing attacks struggle to balance bi-level optimization and efficiency, we revisit poisoning attacks in recommender systems. We put forth a Game-based Co-training Attack (GCoAttack), which frames the proposed CoAttack and TCD as a game-theoretic process.
  arXiv  Detail & Related papers  (2024-01-23T12:07:20Z)
• Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting [74.68371461260946]
  SocialSense is a framework that induces a belief-centered graph on top of an existent social network, along with graph-based propagation to capture social dynamics. Our method surpasses existing state-of-the-art in experimental evaluations for both zero-shot and supervised settings.
  arXiv  Detail & Related papers  (2023-10-20T06:17:02Z)
• Knowledge-enhanced Black-box Attacks for Recommendations [21.914252071143945]
  Deep neural networks-based recommender systems are vulnerable to adversarial attacks. We propose a knowledge graph-enhanced black-box attacking framework (KGAttack) to effectively learn attacking policies. Comprehensive experiments on various real-world datasets demonstrate the effectiveness of the proposed attacking framework.
  arXiv  Detail & Related papers  (2022-07-21T04:59:31Z)
• Federated Social Recommendation with Graph Neural Network [69.36135187771929]
  We propose fusing social information with user-item interactions to alleviate it, which is the social recommendation problem. We devise a novel framework textbfFedrated textbfSocial recommendation with textbfGraph neural network (FeSoG)
  arXiv  Detail & Related papers  (2021-11-21T09:41:39Z)
• PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion [58.870444954499014]
  A common practice is to subsume recommender systems under the decentralized federated learning paradigm. We present a systematic approach to backdooring federated recommender systems for targeted item promotion.
  arXiv  Detail & Related papers  (2021-10-21T06:48:35Z)
• Harnessing the Power of Ego Network Layers for Link Prediction in Online Social Networks [0.734084539365505]
  Predictions are typically based on unsupervised or supervised learning. We argue that richer information about personal social structure of individuals might lead to better predictions. We show that social-awareness generally provides significant improvements in the prediction performance.
  arXiv  Detail & Related papers  (2021-09-19T18:49:10Z)
• HSR: Hyperbolic Social Recommender [3.788467660629549]
  We present Hyperbolic Social Recommender (HSR), a novel social recommendation framework that utilizes hyperbolic geometry to boost the performance. HSR can learn high-quality user and item representations for better modeling user-item interaction and user-user social relations. We show that our proposed HSR outperforms its Euclidean counterpart and state-of-the-art social recommenders in click-through rate prediction and top-K recommendation.
  arXiv  Detail & Related papers  (2021-02-15T12:09:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.