© The Institution of Engineering and Technology
Recent research has shown the significant vulnerabilities of collaborative recommender systems in the face of profile injection attacks, in which malicious users insert fake profiles into the rating database in order to bias the system's output. To reduce this risk, a number of approaches have been proposed to detect such attacks. Although the existing detection approaches can detect the standard type of these attacks effectively, they perform badly when detecting the recently proposed obfuscated type of these attacks, for example, average over popular items (AoP) attack. With this problem in mind, in this study the author propose a supervised approach to detect such attack. First, he uses the theory of term frequency inverse document frequency (TFIDF) to extract the features of AoP attack. Second, he uses the training set to train support vector machine (SVM) to generate a SVM-based classifier. Finally, he uses the generated classifier to detect the AoP attack. The experimental results on MovieLens dataset show that the proposed approach can detect AoP attack with high recall and precision.
References
-
-
1)
-
4. Mobasher, B., Burke, R., Bhaumik, R., et al: ‘Towards trustworthy recommender systems: an analysis of attack models and algorithm robustness’, ACM Trans. Internet Technol., 2007, 7, (4), pp. 23:1–23:38 (doi: 10.1145/1278366.1278372).
-
2)
-
18. He, F., Wang, X., Liu, B.: ‘Attack detection by rough set theory in recommendation system’. 2010 IEEE Int. Conf. on Granular Computing, Silicon Valley, USA, August 2010, pp. 692–695.
-
3)
-
14. Zhang, Z., Kulkarni, S.R.: ‘Detection of shilling attacks in recommender systems via spectral clustering’. Proc. of the 17th Int. Conf. on Information Fusion, Salamanca, Spain, July 2014.
-
4)
-
24. Salton, G.: ‘Developments in automatic text retrieval’, Science, 1991, 253, (5023), pp. 974–980 (doi: 10.1126/science.253.5023.974).
-
5)
-
12. Mehta, B., Thomas, H., Peter, F.: ‘Lies and propaganda: detecting spam users in collaborative filtering’. Proc. of the 12th Int. Conf. on Intelligent User Interfaces, Honolulu, USA, January 2007, pp. 14–21.
-
6)
-
8. Chirita, P.-A., Nejdl, W., Zamfir, C.: ‘Preventing shilling attacks in online recommender systems’. Proc. of the Seventh Annual ACM Int. Workshop on Web Information and Data Management, Bremen, Germany, October 2005, pp. 67–74.
-
7)
-
11. Lee, J.-S., Zhu, D.: ‘Shilling attack detection new approach for a trustworthy recommender system’, INFORMS J. on Comput., 2012, 24, (1), pp. 117–131 (doi: 10.1287/ijoc.1100.0440).
-
8)
-
23. Mahony, M.O., Hurley, N., Kushmerick, N., et al: ‘Collaborative recommendation: a robustness analysis’, ACM Trans. Internet Technol., 2004, 4, (4), pp. 344–377 (doi: 10.1145/1031114.1031116).
-
9)
-
22. Zhang, F.-Z., Zhou, Q.-Q.: ‘Ensemble detection model for profile injection attacks in collaborative recommender systems based on BP neural network’, IET Inf. Sec., 2015, 9, (1), pp. 24–31 (doi: 10.1049/iet-ifs.2013.0145).
-
10)
-
2. Lam, S.K., Riedl, J.: ‘Shilling recommender systems for fun and profit’. Proc. of the 13th Int. Conf. on World Wide Web, New York, USA, May 2004, pp. 393–402.
-
11)
-
5. Burke, R., Mobasher, B., Bhaumik, R.: ‘Limited knowledge shilling attacks in collaborative filtering systems’. Proc. of Workshop on Intelligent Techniques for Web Personalization, Edinburgh, Scotland, July 2005.
-
12)
-
3. Burke, R., Mobasher, B., Williams, C., et al: ‘Detecting profile injection attacks in collaborative recommender systems’. Proc. of the Eighth IEEE Int. Conf. on E-Commerce Technology and the Third IEEE Int. Conf. on Enterprise Computing, E-Commerce, and E-Services, Washington, USA, June 2006, pp. 23:1–23:8.
-
13)
-
6. Williams, C., Mobasher, B., Burke, R., et al: ‘Detection of obfuscated attacks in collaborative recommender systems’. Proc. of the ECAI 2006 Workshop on Recommender Systems, Riva del Grada, Italy, August 2006, pp. 19–23.
-
14)
-
10. Bryan, K., Mahony, M.O., Cunningham, P.: ‘Unsupervised retrieval of attack profiles in collaborative recommender systems’. Proc. of the Second ACM Int. Conf. on Recommender Systems, Lausanne, Switzerland, October 2008, pp. 155–162.
-
15)
-
21. Zhang, F.Z., Zhou, Q.Q.: ‘A meta-learning-based approach for detecting profile injection attacks in collaborative recommender systems’, J. Comput., 2012, 7, (1), pp. 226–234.
-
16)
-
16. Burke, R., Mobasher, B., Williams, C., et al: ‘Classification features for attack detection in collaborative recommender systems’. Proc. of the 12th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, Philadelphia, USA, August 2006, pp. 542–547.
-
17)
-
19. Zhang, Z., Kulkarni, S.R.: ‘Graph-based detection of shilling attacks in recommender systems’. 2013 IEEE Int. Workshop on Machine Learning for Signal Processing, Southampton, UK, September 2013.
-
18)
-
28. Yerima, S.Y., Sezer, S., McWilliams, G.: ‘Analysis of Bayesian classification-based approaches for Android malware detection’, IET Inf. Sec., 2014, 8, (1), pp. 25–36 (doi: 10.1049/iet-ifs.2013.0095).
-
19)
-
26. Chen, Z.-Z., Pears, N., Freeman, M., et al: ‘A Gaussian mixture model and support vector machine approach to vehicle type and colour classification’, IET Intell. Transp. Syst., 2014, 8, (2), pp. 135–144 (doi: 10.1049/iet-its.2012.0104).
-
20)
-
7. Hurley, N., Cheng, Z., Zhang, M.: ‘Statistical attack detection’. Proc. of the Third ACM Conf. on Recommender systems, New York, USA, October 2009, pp. 149–156.
-
21)
-
20. Morid, M.A., Shajari, M., Hashemi, A.R.: ‘Defending recommender systems by influence analysis’, Inf. Retr., 2014, 17, (2), pp. 137–152 (doi: 10.1007/s10791-013-9224-5).
-
22)
-
13. Mehta, B., Nejdl, W.: ‘Unsupervised strategies for shilling detection and robust collaborative filtering’, User Model. User-Adapt. Interact., 2009, 19, (1–2), pp. 65–79 (doi: 10.1007/s11257-008-9050-4).
-
23)
-
1. Cai, Y., Leung, H.-F., Li, Q., et al: ‘Typicality-based collaborative filtering recommendation’, IEEE Trans. Knowl. Data Eng., 2014, 26, (3), pp. 766–779 (doi: 10.1109/TKDE.2013.7).
-
24)
-
9. Su, X.-F., Zeng, H.-J., Chen, Z.: ‘Finding group shilling in recommendation system’. Proc. of the Special Interest Tracks and Posters of the 14th Int. Conf. on World Wide Web, Chiba, Japan, May 2005, pp. 960–961.
-
25)
-
25. Breese, J.S., Heckerman, D., Kadie, C.: ‘Empirical analysis of predictive algorithms for collaborative filtering’. Proc. of the 14th Conf. on Uncertainty in Artificial Intelligence, Madison, Wisconsin, July 1998, pp. 43–52.
-
26)
-
17. Williams, C.A., Mobasher, B., Burke, R., et al: ‘Detecting profile injection attacks in collaborative filtering: a classification-based approach’. Proc. of the Eighth Knowledge Discovery on the Web Int. Conf. on Advances in Web Mining and Web Usage Analysis, Philadelphia, USA, August 2007, pp. 167–186.
-
27)
-
15. Williams, C.A., Mobasher, B., Burke, R.: ‘Defending recommender systems: detection of profile injection attacks’, Serv. Oriented Comput. Appl., 2007, 1, (3), pp. 157–170 (doi: 10.1007/s11761-007-0013-0).
-
28)
-
27. Mehta, B., Nejdl, W.: ‘Attack resistant collaborative filtering’. Proc. of the 31st annual Int. ACM SIGIR Conf. on Research and Development in Information Retrieval, Singapore, July 2008, pp. 75–82.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ifs.2015.0067
Related content
content/journals/10.1049/iet-ifs.2015.0067
pub_keyword,iet_inspecKeyword,pub_concept
6
6