Abstract
Personalization collaborative filtering recommender systems (CFRSs) are the crucial components of popular E-commerce services. In practice, CFRSs are also particularly vulnerable to “shilling” attacks or “profile injection” attacks due to their openness. The attackers can inject well-designed attack profiles into CFRSs in order to bias the recommendation results to their benefits. To reduce this risk, various detection techniques have been proposed to detect such attacks, which use diverse features extracted from user profiles. However, relying on limited features to improve the detection performance is difficult seemingly, since the existing features can not fully characterize the attack profiles and genuine profiles. In this paper, we propose a novel detection method to make recommender systems resistant to such attacks. The existing features can be briefly summarized as two aspects including rating behavior based and item distribution based. We firstly formulate the problem as finding a mapping model between rating behavior and item distribution by exploiting the least-squares approximate solution. Based on the trained model, we design a detector by employing a regressor to detect such attacks. Extensive experiments on both the MovieLens-100K and MovieLens-ml-latest-small datasets examine the effectiveness of the proposed detection method. Experimental results demonstrate the outperformance of the proposed approach in comparison with benchmarked method including KNN.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
The ratio between the number of attackers and genuine users.
The ratio between the number of items rated by user u and the number of entire items in the recommender system.
The ratio between the number of ratings and entire ratings in the rating matrix.
References
Bryan, K., OMahony, M., & Cunningham, P. (2008). Unsupervised retrieval of attack profiles in collaborative recommender systems. In ACM conference on recommender systems (pp. 155–162).
Burke, R., Mobasher, B., & Williams, C. (2006). Classification features for attack detection in collaborative recommender systems. In International conference on knowledge discovery and data mining (pp. 17–20).
Cacheda, F., Carneiro, V., Fernandez, D., & Formoso, V. (2011). Comparison of collaborative filtering algorithms: limitations of current techniques and proposals for scalable, high-performance recommender systems. ACM Transactions on the Web (TWEB), 5(1).
Cao, J., Wu, Z., Mao, B., & Zhang, Y. (2013). Shilling attack detection utilizing semi-supervised learning method for collaborative recommender system. World Wide Web, 16, 729–748.
Chu, E., Gorinevsky, D., & Boyd, S. (2010). Detecting aircraft performance anomalies from cruise flight data. In AIAA infotech aerospace conference (pp. 20–22).
Chung, C., Hsu, P., & Huang, S. (2013). β P: a novel approach to filter out malicious rating profiles from recommender systems. Journal of Decision Support Systems, 55(1), 314–325.
David, M.W. (2011). Evaluation: from precision, recall and f-measure to roc, informedness, markedness correlation. Journal of Machine Learning Technologies.
Gunes, I., Kaleli, C., Bilge, A., & Polat, H. (2012). Shilling attacks against recommender systems: a comprehensive survey. Artificial Intelligence Review, 42(4), 1–33.
He, F., Wang, X., & Liu, B. (2010). Attack detection by rough set theory in recommendation system. In IEEE international conference on granular computing (pp. 692–695).
Hurley, N., OMahony, M., & Silvestre, G. (2007). Attacking recommender systems: a cost-benefit analysis. IEEE Intelligent Systems, 64–68.
Hurley, N., Cheng, Z., & Zhang, M. (2009). Statistical attack detection. In Proceedings of the 3rd ACM conference on recommender systems (RecSys’09) (pp. 149–156).
Jia, D., Zhang, F., & Liu, S. (2013). A robust collaborative filtering recommendation algorithm based on multidimensional trust model. Journal of Software, 8(1).
Li, C., & Luo, Z. (2011). Detection of shilling attacks in collaborative filtering recommender systems. In International conference of soft computing and pattern recognition (pp. 190–193).
Mehta, B., Hofmann, T., & Fankhauser, P. (2007). Lies and propaganda: detecting spam users in collaborative filtering. In Proceedings of the 12th international conference on intelligent user interfaces (IUI’07) (pp. 14–21).
Mobasher, B., Burke, R., & Sandvig, J. (2006). Model-based collaborative filtering as a defense against profile injection attacks. In American Association for Artificial Intelligence.
Mobasher, B., Burke, R., Bhaumil, B., & Williams, C. (2007a). Towards trustworthy recommender systems: an analysis of attack models and algorithm robustness. ACM Transactions on Internet Technology, 7(4), 23–38.
Mobasher, B., Burke, R., Bhaumik, R., & Williams, C. (2007b). Toward trustworthy recommender systems: an analysis of attack models and algorithm robustness. ACM Transactions on Internet Technology (TOIT), 7(4), 38.
Morid, M., & Shajari, M. (2013). Defending recommender systems by influence analysis. Information Retrieval, 17(2), 137–152.
Seminario, C.E. (2013). Accuracy and robustness impacts of power user attacks on collaborative recommender systems. In ACM conference on recommender systems.
Seminario, C.E., & Wilson, D.C. (2014). Attacking item-based recommender systems with power items. In ACM conference on recommender systems (pp. 57–64).
Williams, C.A., Mobasher, B., & Burke, R. (2007a). Defending recommender systems: detection of profile injection attacks. SOCA, 1(3), 157–170.
Williams, C.A., Mobasher, B., Burke, R., & Bhaumik, R. (2007b). Detecting profile injection attacks in collaborative filtering: a classification-based approach. In Advances in web mining and web usage analysis (pp. 167–186).
Wu, Z.A., Wu, J.J., Cao, J., & Tao, D.C. (2012). HySAD: a semi-supervised hybrid shilling attack detector for trustworthy product recommendation. In ACM SIGKDD conference on knowledge discovery and data mining (pp. 985–993).
Zhang, Z., & Kulkarni, S. (2013). Graph-based detection of shilling attacks in recommender systems. In IEEE international workshop on machine learning for signal processing (pp. 1–6).
Zhang, F., & Zhou, Q. (2012). A meta-learning-based approach for detecting profile injection attacks in collaborative recommender systems. Journal on Computing, 7(1), 226–234.
Zhang, F., & Zhou, Q. (2014). HHT-SVM: an online method for detecting profile injection attacks in collaborative recommender systems. Knowledge-Based Systems, 65, 96–105.
Zhou, W., Koh, Y.S., Wen, J.H., Burki, S., & Dobbie, G. (2014). Detection of abnormal profiles on group attacks in recommender systems. In Proceedings of the 37th international ACM SIGIR conference on Research on development in information retrieval (pp. 955–958).
Zou, J., & Fekri, F. (2013). A belief propagation approach for detecting shilling attacks in collaborative filtering. In Proceedings of the 22nd ACM international conference on conference on information & knowledge management (CIKM) (pp. 1837–1840).
Acknowledgment
The research is supported by the National Natural Science Foundation (61175039, 61375040), International Research Collaboration Project of Shaanxi Province (2013KW11) and Fundamental Research Funds for Central Universities (2012jdhz08). One anonymous reviewer has carefully read this paper and has provided to us numerous constructive suggestions. As a result, the overall quality of the paper has been noticeably enhanced, to which we feel much indebted and are grateful.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Disclosure of potential conflicts of interest
The authors declare that they have no competing interests.
Research involving Human Participants and/or Animals
All two authors contributed equally to this work. They all read and approved the final version of the manuscript.
Informed consent
School of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, P.R. China.
Additional information
The research is supported by the National Natural Science Foundation (61175039, 61375040), International Research Collaboration Project of Shaanxi Province (2013KW11) and Fundamental Research Funds for Central Universities (2012jdhz08).
Rights and permissions
About this article
Cite this article
Yang, Z., Cai, Z. Detecting abnormal profiles in collaborative filtering recommender systems. J Intell Inf Syst 48, 499–518 (2017). https://doi.org/10.1007/s10844-016-0424-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10844-016-0424-5