SRSPIA: Security Based Recommender System Against Profile Injection Attack

SRSPIA: Security Based Recommender System Against Profile Injection Attack

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2021 by IJETT Journal
Volume-69 Issue-3
Year of Publication : 2021
Authors : Anjani Kumar Verma, Veer Sain Dixit
DOI :  10.14445/22315381/IJETT-V69I3P233

Citation 

MLA Style: Anjani Kumar Verma, Veer Sain Dixit"SRSPIA: Security Based Recommender System Against Profile Injection Attack" International Journal of Engineering Trends and Technology 69.3(2021):219-228. 

APA Style:Anjani Kumar Verma, Veer Sain Dixit. SRSPIA: Security Based Recommender System Against Profile Injection Attack  International Journal of Engineering Trends and Technology, 69(3),219-228.

Abstract
Information produced by users in terms of rating movies is a major ingredient on the web. Information filtering is the most popular way to obtain precise information that could be used for different e-commerce applications for branding and popularity. Today, security is the most prominent aspect of the safety of data available online. In this work, a novel Security- based Recommender System against Profile Injection attacks (SRSPIA) has been proposed for movies that consist of three phases. In the first phase, the collection of the data is crawled based on user rating behaviors on the movie(s) without the security integration in the system. In the second phase, the collection of the data is crawled after the security integration in the system. In the third phase, a model is designed which works in two modes. In the first mode, the different machine learning supervised classifiers are applied with the two datasets obtained from the above two phases individually. In the second mode, ensemble methods are applied to these datasets. It is observed that the accuracy has been improved with the ensemble approach on various performance evaluation metrics that have been used for analyzing the system. However, the performance is evaluated on this model and found that the results in the case of the proposed system dataset phase 2 show better accuracy in comparison to another phase and dataset.

Reference
[1] Burke, R., Mobasher, B., Williams, C., & Bhaumik, R. (2006, August). Classification features for attack detection in collaborative recommender systems. In Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 542-547).
[2] Williams, C. A., Mobasher, B., Burke, R., & Bhaumik, R. (2006, August). Detecting profile injection attacks in collaborative filtering: a classification-based approach. In International Workshop on Knowledge Discovery on the Web (pp. 167-186). Springer, Berlin, Heidelberg.
[3] Lam, S. K., & Riedl, J. (2004, May). Shilling recommender systems for fun and profit. In Proceedings of the 13th international conference on World Wide Web (pp. 393-402).
[4] Secure system for movie review and rating: SRSPIA. (2019). https://projectatcic.online/ Accessed 12 October 2019.
[5] Verma, A. K., & Dixit, V. S. (2019). A Comparative Evaluation of Profile Injection Attacks. In Advances in Data and Information Sciences (pp. 43-52). Springer, Singapore.
[6] Miyahara, K., & Pazzani, M.J. (2002). Improvement of Collaborative Filtering with the Simple Bayesian Classifier 1.
[7] Kumari, T., & Bedi, P. (2017). A comprehensive study of shilling attacks in recommender systems. International Journal of Computer Science Issues (IJCSI), 14(4), 44.
[8] Bobadilla, J., Ortega, F., Hernando, A., & Gutiérrez, A. (2013). Recommender systems survey. Knowledge-based systems, 46, 109-132.
[9] Wu, M. L., Chang, C. H., & Liu, R. Z. (2014). Integrating content-based filtering with collaborative filtering using co-clustering with augmented matrices. Expert Systems with Applications, 41(6), 2754-2761.
[10] Al-Shamri, M. Y. H. (2016). User profiling approaches for demographic recommender systems. Knowledge-Based Systems, 100, 175-187.
[11] Yu, J., Gao, M., Rong, W., Song, Y., & Xiong, Q. (2017). A social recommender based on factorization and distance metric learning. IEEE Access, 5, 21557-21566.
[12] Yang, Z., Wu, B., Zheng, K., Wang, X., & Lei, L. (2016). A survey of collaborative filtering-based recommender systems for mobile internet applications. IEEE Access, 4, 3273-3287.
[13] Bobadilla, J., Hernando, A., Ortega, F., & Gutiérrez, A. (2012). Collaborative filtering based on significances. Information Sciences, 185(1), 1-17.
[14] Paradarami, T. K., Bastian, N. D., & Wightman, J. L. (2017). A hybrid recommender system using artificial neural networks. Expert Systems with Applications, 83, 300-313.
[15] Wang, Y., Qian, L., Li, F., & Zhang, L. (2018). A comparative study on shilling detection methods for trustworthy recommendations. Journal of Systems Science and Systems Engineering, 27(4), 458-478.
[16] Chirita, P. A., Nejdl, W., & Zamfir, C. (2005, November). Preventing shilling attacks in online recommender systems. In Proceedings of the 7th annual ACM international workshop on Web information and data management (pp. 67-74).
[17] Burke, R., Mobasher, B., Williams, C., & Bhaumik, R. (2006, August). Classification features for attack detection in collaborative recommender systems. In Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 542-547).
[18] Zhang, S., Ouyang, Y., Ford, J., & Makedon, F. (2006, August). Analysis of a low-dimensional linear model under recommendation attacks. In Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval (pp. 517-524).
[19] Li, X., Gao, M., Rong, W., Xiong, Q., & Wen, J. (2016, June). Shilling attacks analysis in collaborative filtering based web service recommendation systems. In 2016 IEEE International Conference on Web Services (ICWS) (pp. 538-545). IEEE.
[20] Cao, J., Wu, Z., Mao, B., & Zhang, Y. (2013). Shilling attack detection utilizing the semi-supervised learning method for collaborative recommender system. World Wide Web, 16(5-6), 729-748.
[21] CSPIT, C. (2016). A Novel Supervised Approach to Detection of Shilling Attack in Collaborative Filtering Based Recommendation System. International Journal of Computer Science and Information Security (IJCSIS), 14(4).
[22] Hernando, A., Bobadilla, J., & Ortega, F. (2016). A non-negative matrix factorization for collaborative filtering recommender systems based on a Bayesian probabilistic model. Knowledge-Based Systems, 97, 188-202.
[23] Mehta, B., & Nejdl, W. (2009). Unsupervised strategies for shilling detection and robust collaborative filtering. User Modeling and User-Adapted Interaction, 19(1-2), 65-97.
[24] Zhang, F., Deng, Z. J., He, Z. M., Lin, X. C., & Sun, L. L. (2018, July). Detection of shilling attack in collaborative filtering recommender system by PCA and data complexity. In 2018 International Conference on Machine Learning and Cybernetics (ICMLC) (Vol. 2, pp. 673-678). IEEE.
[25] He, W., Xu, G., Wang, Y., Wu, Z., Bu, Z., Cao, J., & Yang, D. (2016). Discovering shilling groups in a real e-commerce platform. Online Information Review.
[26] Lee, J. S., & Zhu, D. (2012). Shilling attack detection—a new approach for a trustworthy recommender system. INFORMS Journal on Computing, 24(1), 117-131.
[27] 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.
[28] Hao, Y., & Zhang, F. (2018). Detecting shilling profiles in collaborative recommender systems via multidimensional profile temporal features. IET Information Security, 12(4), 362-374.
[29] Dhimmar, J. H., & Chauhan, R. (2015). An accuracy improvement of detection of profile-injection attacks in recommender systems using outlier analysis. International Journal of Computer Applications, 122(10).
[30] Chirita, P. A., Nejdl, W., & Zamfir, C. (2005, November). Preventing shilling attacks in online recommender systems. In Proceedings of the 7th annual ACM international workshop on Web information and data management (pp. 67-74).
[31] Su, X. F., Zeng, H. J., & Chen, Z. (2005, May). Finding group shilling in the recommendation system. In Special interest tracks and posters of the 14th international conference on World Wide Web (pp. 960-961).
[32] Bryan, K., O`Mahony, M., & Cunningham, P. (2008, October). Unsupervised retrieval of attack profiles in collaborative recommender systems. In Proceedings of the 2008 ACM conference on Recommender systems (pp. 155-162).
[33] Lee, J. S., & Zhu, D. (2012). Shilling attack detection—a new approach for a trustworthy recommender system. INFORMS Journal on Computing, 24(1), 117-131.
[34] Mehta, B., Hofmann, T., & Fankhauser, P. (2007, January). Lies and propaganda: detecting spam users in collaborative filtering. In Proceedings of the 12th international conference on Intelligent user interfaces (pp. 14-21).
[35] Mehta, B., & Nejdl, W. (2009). Unsupervised strategies for shilling detection and robust collaborative filtering. User Modeling and User-Adapted Interaction, 19(1-2), 65-97.
[36] Williams, C. A., Mobasher, B., & Burke, R. (2007). Defending recommender systems: detection of profile injection attacks. Service-Oriented Computing and Applications, 1(3), 157-170.
[37] Burke, R., Mobasher, B., Williams, C., & Bhaumik, R. (2006, August). Classification features for attack detection in collaborative recommender systems. In Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 542-547).
[38] Williams, C. A., Mobasher, B., Burke, R., & Bhaumik, R. (2006, August). Detecting profile injection attacks in collaborative filtering: a classification-based approach. In International Workshop on Knowledge Discovery on the Web (pp. 167-186). Springer, Berlin, Heidelberg.
[39] He, F., Wang, X., & Liu, B. (2010, August). Attack detection by rough set theory in the recommendation system. In 2010 IEEE International Conference on Granular Computing (pp. 692-695). IEEE.
[40] Mobasher, B., Burke, R., Bhaumik, R., & Williams, C. (2005, August). Effective attack models for shilling item-based collaborative filtering systems. In Proceedings of the WebKDD Workshop (pp. 13-23). Citeseer.
[41] MovieLens Dataset 1M. (2019). https://grouplens.org/datasets/movielens/1m/ Accessed 21 December 2019.
[42] John, G. H., & Langley, P. (1995). Estimating Continuous Distributions in Bayesian Classifiers. In Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence.
[43] Buntine, W. L. (1994). Operations for learning with graphical models. Journal of artificial intelligence research, 2, 159-225.
[44] Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
[45] Chang, C. C., & Lin, C. J. (2011). LIBSVM: A library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2(3), 1-27.
[46] Breiman, L. (1996). Bagging predictors. Machine learning, 24(2), 123-140.
[47] Weka 3: Machine Learning Software in Java. (2019). “https://www.cs.waikato.ac.nz/~ml/weka/” Accessed 11 March 2019.
[48] Chirita, P. A., Nejdl, W., & Zamfir, C. (2005, November). Preventing shilling attacks in online recommender systems. In Proceedings of the 7th annual ACM international workshop on Web information and data management (pp. 67-74).
[49] Alonso, S., Bobadilla, J., Ortega, F., & Moya, R. (2019). Robust model-based reliability approach to tackle shilling attacks in collaborative filtering recommender systems. IEEE Access, 7, 41782-41798.
[50] Kaur, P., & Goel, S. (2016, August). Shilling attack models in recommender system. In 2016 International Conference on Inventive Computation Technologies (ICICT) (Vol. 2, pp. 1-5). IEEE.

Keywords
Recommender Systems, Profile injection attack, Security, Classifiers, MAE