DM-FedMF: A Recommendation Model of Federated Matrix Factorization With Detection Mechanism

Abstract

Items are recommended to users by the federated recommendation system while protecting user privacy, but there is a risk of the performance of the global model being seriously affected by malicious clients through the tampering of local data and model parameters. In this paper, a federated matrix factorization recommendation model with a detection mechanism(DM-FedMF) is proposed. The experimental analysis concludes that there is a gradient difference in item preference parameters between malicious and benign clients. Accordingly, an objective function is designed to measure item preference differences as a means of identifying malicious clients on the server. Secondly, a malicious client reporting mechanism is proposed to count the reported frequency of all clients and set a threshold. Based on the number of honest clients, the list of attackers is updated. Finally, the malicious client is detected and eliminated based on the list of attackers. The other three defense algorithms are compared with two public datasets in this paper. The experimental results show that the detection mechanism can effectively defend against data poisoning attacks, category attacks, noise attacks, and sign flipping attacks, and the performance of the model's recommendations is better than that achieved by applying other defense methods.