Deep Leakage From Horizontal Federated Sequential Recommender Systems

被引:0
|
作者
Guo, Kaifeng [1 ]
Xie, Kesheng [1 ]
Shi, Zian [1 ]
Gao, Rongjian [1 ]
机构
[1] Fuzhou Univ, Maynooth Int Engn Coll, Fuzhou 350108, Peoples R China
来源
IEEE ACCESS | 2024年 / 12卷
关键词
Computational modeling; Recommender systems; Data models; Training; Servers; Differential privacy; Accuracy; Federated learning; Privacy breach; Predictive models; Shared gradients; privacy safeguarding; model parameters; recommendation systems; defensive measures; deep learning; artificial intelligence;
D O I
10.1109/ACCESS.2024.3498699
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Shared gradients are extensively utilized for safeguarding the privacy of training data. However, an increasing body of research is uncovering that the gradients or model parameters transmitted in distributed systems may also leak users' private information. A majority of these studies are predicated on intercepting the data transmitted by individual users to derive their private information. A smaller portion of research can extrapolate a multitude of users' private data through the average gradients passed by the server. These investigations have analyzed information leakage in image and text domains, yet have not explored the leakage issues inherent within recommendation systems operating in distributed environments. Furthermore, the impact of batch size and model parameters on the degree of leakage has not been sufficiently analyzed. This paper proposes that within recommendation systems, it is feasible to infer the encapsulated user privacy data by receiving average gradients or model parameters provided by the server. Additionally, the paper evaluates the extent to which various parameters within the system impact the leakage and presents corresponding defensive measures while assessing their efficacy.
引用
收藏
页码:173037 / 173046
页数:10
相关论文
共 50 条
  • [31] PTF-FSR: A Parameter Transmission-Free Federated Sequential Recommender System
    Yuan, Wei
    Yang, Chaoqun
    Qu, Liang
    Hung, Nguyen Quoc Viet
    Ye, Guanhua
    Yin, Hongzhi
    ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2025, 43 (02)
  • [32] Collaborative Deep Learning for Recommender Systems
    Wang, Hao
    Wang, Naiyan
    Yeung, Dit-Yan
    KDD'15: PROCEEDINGS OF THE 21ST ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2015, : 1235 - 1244
  • [33] Towards a Deep Attention-Based Sequential Recommender System
    Yakhchi, Shahpar
    Beheshti, Amin
    Ghafari, Seyed-Mohssen
    Orgun, Mehmet A.
    Liu, Guanfeng
    IEEE ACCESS, 2020, 8 : 178073 - 178084
  • [34] A Generic Network Compression Framework for Sequential Recommender Systems
    Sun, Yang
    Yuan, Fajie
    Yang, Min
    Wei, Guoao
    Zhao, Zhou
    Liu, Duo
    PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20), 2020, : 1299 - 1308
  • [35] Sequential Nature of Recommender Systems Disrupts the Evaluation Process
    Shirali, Ali
    ADVANCES IN BIAS AND FAIRNESS IN INFORMATION RETRIEVAL, BIAS 2022, 2022, 1610 : 21 - 34
  • [36] Exploration in Sequential Recommender Systems via Graph Representations
    Kiselev, Dmitrii
    Makarov, Ilya
    IEEE Access, 2022, 10 : 123614 - 123621
  • [37] Recommender systems using temporal restricted sequential patterns
    Galarreta A.-P.
    Samamé H.
    Maehara Y.
    Nunez-del-Prado M.
    Alatrista-Salas H.
    Journal of Ambient Intelligence and Humanized Computing, 2023, 14 (12) : 15895 - 15908
  • [38] Modeling the sequential behaviors of online users in recommender systems
    Tuc Nguyen
    Linh Ngo
    Khoat Than
    ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS II, 2020, 11413
  • [39] Exploration in Sequential Recommender Systems via Graph Representations
    Kiselev, Dmitrii
    Makarov, Ilya
    IEEE ACCESS, 2022, 10 : 123614 - 123621
  • [40] The Deep Flow Inspection Framework Based on Horizontal Federated Learning
    Wei, Tongyan
    Wang, Ying
    Li, Wenjing
    2022 23RD ASIA-PACIFIC NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM (APNOMS 2022), 2022, : 379 - 382