Robust Analysis on a Privacy Preserving Recommendation Algorithm under the KNN Attack

Abstract:

— Among algorithms in recommendation system, Collaborative Filtering (CF) is a popular one. However, the CF methods can’t guarantee the safety of the user rating data which cause private preserving issue. In general, there are four kinds of methods to solve private preserving: Perturbation, randomization, swapping and encryption. In this paper, we mimic algorithms which attack the privacy-preserving methods with randomized perturbation techniques. After leaking part of rating history of a customer, we can infer this customer’s other rating history. At the end, we propose an algorithm to enhance the system so as to avoid being attacked.

• Periodical: Applied Mechanics and Materials (Volume 610)
• Pages: 717-721
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.610.717
• Online since: August 2014
• Authors: Yan Gao, Jing Bo Xia*, Jing Jing Ji, Ling Ma
• Keywords: Accuracy, Collaborative Filtering (CF), KNN Attack, Privacy-Preserving, Recommendation System

References

[1] Yin, Chun-Xia, and Qin-Ke Peng. A careful assessment of recommendation algorithms related to dimension reduction techniques. Knowledge-Based Systems 27 (2012): 407-423.

DOI: 10.1016/j.knosys.2011.11.022

[2] Zhu, Tianqing, et al. An effective privacy preserving algorithm for neighborhood-based collaborative filtering. Future Generation Computer Systems (2013).

DOI: 10.1016/j.future.2013.07.019

[3] Ren Y, Li G, Zhang J, et al. The efficient imputation method for neighborhood-based collaborative filtering. Proceedings of the 21st ACM international conference on Information and knowledge management. ACM, 2012: 684-693.

DOI: 10.1145/2396761.2396849

[4] Calandrino J A, Kilzer A, Narayanan A, et al. You Might Also Like:, Privacy Risks of Collaborative Filtering Security and Privacy (SP), 2011 IEEE Symposium on. IEEE, 2011: 231-246.

DOI: 10.1109/sp.2011.40

[5] Bilge A, Polat H. A comparison of clustering-based privacy-preserving collaborative filtering schemes. Applied Soft Computing, 2013, 13(5): 2478-2489.

DOI: 10.1016/j.asoc.2012.11.046

[6] Canny J. Collaborative filtering with privacy, IEEE Symposium on Security and Privacy. IEEE, 2002: 45-57.

DOI: 10.1109/secpri.2002.1004361

[7] Kaleli C, Polat H. Providing private recommendations using naive Bayesian classifier[M]/Advances in Intelligent Web Mastering. Springer Berlin Heidelberg, 2007: 168-173.

DOI: 10.1007/978-3-540-72575-6_27

[8] Chen G, Wang F, Zhang C. Collaborative filtering using orthogonal nonnegative matrix tri-factorization. Information Processing & Management, 2009, 45(3): 368-379.

DOI: 10.1016/j.ipm.2008.12.004

[9] Russell S, Yoon V. Applications of wavelet data reduction in a recommender system. Expert Systems with Applications, 2008, 34(4): 2316-2325.

DOI: 10.1016/j.eswa.2007.03.009

[10] Kim H N, Ji A T, Ha I, et al. Collaborative filtering based on collaborative tagging for enhancing the quality of recommendation. Electronic Commerce Research and Applications, 2010, 9(1): 73-83.

DOI: 10.1016/j.elerap.2009.08.004

[11] Lee S K, Cho Y H, Kim S H. Collaborative filtering with ordinal scale-based implicit ratings for mobile music recommendations. Information Sciences, 2010, 180(11): 2142-2155.

DOI: 10.1016/j.ins.2010.02.004

[12] Kaleli C, Polat H. SOM-based recommendations with privacy on multi-party vertically distributed data [J]. Journal of the Operational Research Society, 2012, 63(6): 826-838.

DOI: 10.1057/jors.2011.76

[13] Bilge A, Polat H. An improved privacy-preserving DWT-based collaborative filtering scheme. Expert Systems with Applications, 2012, 39(3): 3841-38.

DOI: 10.1016/j.eswa.2011.09.094