Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios

Abstract

Various attack methods against recommender systems have been proposed in the past years, and the security issues of recommender systems have drawn considerable attention. Traditional attacks attempt to make target items recommended to as many users as possible by poisoning the training data. Benifiting from the feature of protecting users' private data, federated recommendation can effectively defend such attacks. Therefore, quite a few works have devoted themselves to developing federated recommender systems. For proving current federated recommendation is still vulnerable, in this work we probe to design attack approaches targeting deep learning based recommender models in federated learning scenarios. Specifically, our attacks generate poisoned gradients for manipulated malicious users to upload based on two strategies (i.e., random approximation and hard user mining). Extensive experiments show that our well-designed attacks can effectively poison the target models, and the attack effectiveness sets the state-of-the-art.

This paper has been accepted by the 31st International Joint Conference on Artificial Intelligence (IJCAI-22, Main Track)

References in corpus (5)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System
• Data Poisoning Attacks on Factorization-Based Collaborative Filtering
• Data Poisoning Attacks to Deep Learning Based Recommender Systems
• FedRecAttack: Model Poisoning Attack to Federated Recommendation

Cited by in corpus (5)

• Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning
• A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
• Preventing the Popular Item Embedding Based Attack in Federated Recommendations
• Clean-image Backdoor Attacks
• Blockchain-based Federated Recommendation with Incentive Mechanism