SI Mingdan, LI Qingshan. L2, 1-Norm Regularized Matrix Completion for Attack Detection in Collaborative Filtering Recommender Systems[J]. Chinese Journal of Electronics, 2019, 28(5): 906-915. doi: 10.1049/cje.2019.06.010
Citation: SI Mingdan, LI Qingshan. L2, 1-Norm Regularized Matrix Completion for Attack Detection in Collaborative Filtering Recommender Systems[J]. Chinese Journal of Electronics, 2019, 28(5): 906-915. doi: 10.1049/cje.2019.06.010

L2, 1-Norm Regularized Matrix Completion for Attack Detection in Collaborative Filtering Recommender Systems

doi: 10.1049/cje.2019.06.010
Funds:  This work is supported by the National Natural Science Foundation of China (No.61672401, No.61373045), the Fundamental Research Funds for the Central Universities of China (No.JBG161002), and the Pre-Research Project of the "Thirteenth Five-Year-Plan" of China.
More Information
  • Corresponding author: LI Qingshan (corresponding author) was born in 1973.He received the in computer application technology from Xidian University in 2003.He is a professor of Xidian University.His research interests include meta-search technology,social research technology,multi-agent technology and software engineering.(
  • Received Date: 2017-02-15
  • Rev Recd Date: 2017-09-05
  • Publish Date: 2019-09-10
  • Collaborative filtering recommender systems (CFRSs) are known to be highly vulnerable to profile injection attacks, in which malicious users insert fake profiles into the rating database in order to bias the systems' output, since their openness, and attack detection is still a challenging problem in CFRSs. In order to provide more accurate recommendations, many schemas have been proposed to detect such shilling attacks. However, almost all of them are proposed to detect one or several specific attack types, and few of them can handle hybrid attack types, which usually happen in practice. With this problem in mind, we propose a novel L2, 1-norm regularized matrix completion incorporating prior information (LRMCPI) model to detect shilling attacks by combining matrix completion and L2, 1-norm. The proposed LRMCPI formalizes the attack detection problem as a missing value estimation problem, and it is appropriate because the user-item rating matrix is approximately low-rank and attack profiles could be considered as structural noise. The proposed LRMCPI model not only can better recover the rating matrix using correct rating value but also can detect the positions where the attackers are injected. We evaluate our model on three well-known data sets with different density and the experimental results show that our model outperforms baseline algorithms in both single and hybrid attack types.
  • loading
  • J. Bobadilla, F. Ortega, A. Hernando, et al., "Two decades of recommender systems at", IEEE Educational Activities Department, Vol.21, No.3, pp.12-18, 2017.
    B. Mobasher, R. Burke, C. Williams, et al., "Analysis and detection of segment-focused attacks against collaborative recommendation", International Workshop on Knowledge Discovery on the Web, Springer, Berlin, Heidelberg, pp.96-118, 2005.
    Z. Yang, L. Xu, Z. Cai, et al., "Re-scale AdaBoost for attack detection in collaborative filtering recommender systems", Knowledge-Based Systems, Vol.100, pp.74-88, 2016.
    M.P. O' Mahony, N.J. Hurley and G.C.M. Silvestre, "Collaborative filtering-safe and sound?", 14th International Symposium on Methodologies for Intelligent Systems, Maebashi City, Japan, pp.506-510, 2003.
    R. Bhaumik, B. Mobasher, and R. Burke, "A clustering approach to unsupervised attack detection in collaborative recommender systems", Proc. of IEEE International Conference on Data Mining, Las Vegas, NV, USA, pp.181-187, 2011.
    I. Gunes, C. Kaleli, A. Bilge, et al., "Shilling attacks against recommender systems:A comprehensive survey", Artificial Intelligence Review, Vol.42, No.4, pp.767-799, 2014.
    H. Yi and F. Zhang, "Robust recommendation method based on suspicious users measurement and multidimensional trust", Journal of Intelligent Information Systems, Vol.46, No.2, pp.349-367, 2016.
    A. Bilge, I. Gunes and H. Polat, "Robustness analysis of privacy-preserving model-based recommendation schemes", Expert Systems with Applications, Vol.41, No.8, pp.3671-3681, 2014.
    P.A. Chirita, W. Nejdl and C. Zamfir, "Preventing shilling attacks in online recommender systems", Proc. of ACM International Workshop on Web Information and Data Management, Bremen, Germany, pp.67-74, 2005.
    K. Bryan, M. O'Mahony and P. Cunningham, "Unsupervised retrieval of attack profiles in collaborative recommender systems", Proc. of the 2008 ACM conference on Recommender systems, Lousanne, Switzerland, pp.155-162, 2008.
    H. Yu, "An algorithm for detecting recommendation attack based on incremental learning", Journal of Information & Computational Science, Vol.11, No.7, pp.2365-2373, 2014.
    A. Bilge, Z. Ozdemir and H. Polat, "A novel shilling attack detection method", Procedia Computer Science, Vol.31, pp.165-174, 2014.
    Z. Wu, J. Wu, J. Cao, et al., "HySAD:A semisupervised hybrid shilling attack detector for trustworthy product recommendation", Proc. of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Beijing, China, pp.985-993, 2012.
    C.A. Williams, A. Research and B. Mobasher, "Thesis:Profile injection attack detection for securing collaborative recommender systems", Service Oriented Computing & Applications, Vol.1, No.3, pp.157-170, 2012.
    R. Burke, M.P. O' Mahony and N.J. Hurley, "Robust collaborative recommendation", IEEE International Conference on Communication Systems, Reykjavík, Iceland, pp.36-40, 2015.
    L. Chen, G. Yang, Z.Y. Chen, et al., "Linearized Bregman iteration algorithm for matrix completion with structural noise", Journal of Computer Science, Vol.38, No.7, pp.1357-1371, 2015. (In Chinese)
    B. Mobasher, R. Burke, R. Bhaumik, et al., "Attacks and remedies in collaborative recommendation", IEEE Intelligent Systems, Vol.22, No.3, pp.56-63, 2007.
    Z. Yang, Z. Cai, Y. Yang, et al., "Spotting anomalous ratings for rating systems by analyzing target users and items", Neurocomputing, Vol.240, pp.25-46, 2017.
    Y. Hu, D. Zhang, J. Liu, et al., "Accelerated singular value thresholding for matrix completion", Proc. of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, USA, pp.298-306, 2012.
    L. Yu, C. Liu and Z.K. Zhang, "ulti-linear interactive matrix factorization", Knowledge-Based Systems, Vol.85, pp.307-315, 2015.
    E.J. Candès and B. Recht, "Exact matrix completion via convex optimization", Foundations of Computational Mathematics, Vol.9, No.6, pp.717-772, 2009.
    Z. Wu, Y. Wang, Y. Wang, et al., "Spammers detection from product reviews:A hybrid model", IEEE International Conference on Data Mining, Barcelona, Spain, pp.1039-1044, 2016.
    S. Boyd and L. Vandenberghe, Convex Optimization, Cambridge university press, Cambridge, UK, 2004.
    L.M. Brègman, "The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming", Ussr Computational Mathematics & Mathematical Physics, Vol.7, No.3, pp.200-217, 1967.
    J.F. Cai, E.J. Candès and Z. Shen, "A singular value thresholding algorithm for matrix completion", SIAM Journal on Optimization, Vol.20, No.4, pp.1956-1982, 2010.
    P.L. Combettes and V.R. Wajs, "Signal recovery by proximal forward-backward splitting", Multiscale Modeling & Simulation, Vol.4, No.4, pp.1168-1200, 2005.
    G. Liu, Z. Lin, S. Yan, et al., "Robust recovery of subspace structures by low-rank representation", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.35, No.1, pp.171-184, 2013.
    Y. Koren, "The bellkor solution to the netflix grand prize", Netflix Prize Documentation, Vol.81, pp.1-10, 2009.
    P. Massa and P. Avesani, "Trust-aware recommender systems", Proc. of the 2007 ACM conference on Recommender systems, Minneapolis, Minnesota, USA, pp.17-24, 2007.
  • 加载中


    通讯作者: 陈斌,
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (124) PDF downloads(209) Cited by()
    Proportional views


    DownLoad:  Full-Size Img  PowerPoint