ROBUSTNESS ANALYSIS OF GENETIC ALGORITHM-BASED PRIVACY-PRESERVING RECOMMENDATION ALGORITHMS

Year 2025, Volume: 26 Issue: 3, 246 - 259, 25.09.2025

İhsan Güneş , Mustafa Kemal Birgin

https://doi.org/10.18038/estubtda.1672606

Abstract

Privacy-preserving collaborative filtering (PPCF) denotes a methodology that recommends items to users according to their interests or behaviors while safeguarding user privacy and data confidentiality. PPCF is especially crucial in situations involving sensitive user data, such as purchase history, surfing activity, or personal preferences. Privacy-preserving model-based recommendation methods are preferred over privacy-preserving memory-based schemes due to their online efficiency. There is a lot of work in the literature on model-based CF and PPCF schemes. Model-based prediction algorithms without privacy concerns have been adequately studied in terms of shilling attacks. However, there is a limited number of studies that measure the robustness of model-based PPCF schemes against shilling attacks. PPCF schemes can also be affected by shilling attacks, as can model-based prediction algorithms without privacy concerns. In this study, we investigate the robustness of genetic algorithm based PPCF schemes against shilling attacks. In this paper firstly, we apply masked data-based profile injection attacks to genetic algorithm-based PPCF prediction algorithms. Then, we perform extensive experiments using real data to evaluate their robustness against profile injection attacks. We then compare other model-based methods that have been studied in the literature in terms of robustness. Our empirical analyses show that the model-based scheme with privacy is very robust against shilling attacks.

Keywords

Genetic algorithms , Collaborative filtering , Privacy , Recommendation system , Shilling attacks

References

• [1] Schafer JB, Konstan JA, Riedl J. E-Commerce recommendation applications. In: Springer eBooks, 2001; 2001:115-153. https://doi.org/10.1007/978-1-4615-1627-9_6.
• [2] Bobadilla J, Ortega F, Hernando A, Gutiérrez A. Recommender systems survey. Knowledge-Based Systems, 2013; 46:109-132. https://doi.org/10.1016/j.knosys.2013.03.012.
• [3] Polat H, Du W. Privacy-preserving collaborative filtering using randomized perturbation techniques. In: Third IEEE International Conference on Data Mining. IEEE, 2003:625-628.
• [4] O’Mahony MP, Hurley NJ, Silvestre GCM. Promoting Recommendations: an attack on collaborative filtering. In: Lecture Notes in Computer Science, 2002; 2002:494-503. https://doi.org/10.1007/3-540-46146-9_49.
• [5] O’Mahony MP, Hurley NJ, Silvestre GCM. Towards robust collaborative filtering. In: Lecture Notes in Computer Science, 2002; 2002:87-94. https://doi.org/10.1007/3-540-45750-x_11.
• [6] O’Mahony M, Hurley N, Kushmerick N, Silvestre G. Collaborative recommendation. ACM Transactions on Internet Technology, 2004; 4(4):344-377. https://doi.org/10.1145/1031114.1031116.
• [7] Burke R, Mobasher B, Bhaumik R, Williams C. Collaborative recommendation vulnerability to focused bias injection attacks. In: International Conference on Data Mining: Workshop on Privacy and Security Aspects of Data Mining (ICDM 2005), 2005.
• [8] Birgin MK, Bilge A. Genetic algorithm-based privacy preserving collaborative filtering. In: 2019 Innovations in Intelligent Systems and Applications Conference (ASYU) IEEE; 2019:1-5.
• [9] Polat H, Du W. SVD-based collaborative filtering with privacy. In: Proceedings of the 2005 ACM Symposium on Applied Computing, 2005:791-795.
• [10] Bilge A, Polat H. An improved privacy-preserving DWT-based collaborative filtering scheme. Expert Systems with Applications, 2011;39(3):3841-3854. https://doi.org/10.1016/j.eswa.2011.09.094.
• [11] Bilge A, Gunes I, Polat H. Robustness analysis of privacy-preserving model-based recommendation schemes. Expert Systems With Applications, 2013;41(8):3671-3681. https://doi.org/10.1016/j.eswa.2013.11.039.
• [12] Mobasher B, Burke R, Bhaumik R, Williams C. Toward trustworthy recommender systems: An analysis of attack models and algorithm robustness. ACM Transactions on Internet Technology (TOIT), 2007;7(4):23-es.
• [13] Mobasher B, Burke R, Bhaumik R, Sandvig JJ. Attacks and remedies in collaborative recommendation. IEEE Intell Syst, 2007;22(3):56-63.
• [14] Burke R, Mobasher B, Zabicki R, Bhaumik R. Identifying attack models for secure recommendation. Beyond Personalization, 2005;2005.
• [15] Sandvig JJ, Mobasher B, Burke RD. A survey of collaborative recommendation and the robustness of model-based algorithms. IEEE Data Eng Bull, 2008;31(2):3-13.
• [16] Zhang F. A survey of shilling attacks in collaborative filtering recommender systems. In: 2009 International Conference on Computational Intelligence and Software Engineering, IEEE; 2009:1-4.
• [17] Rezaimehr F, Dadkhah C. T&TRS: robust collaborative filtering recommender systems against attacks. Multimedia Tools and Applications, 2023;83(11):31701-31731. https://doi.org/10.1007/s11042-023-16641-x.
• [18] Singh PK, Pramanik PKD, Sinhababu N, Choudhury P. Detecting unknown shilling attacks in recommendation systems. Wireless Personal Communications, 2024;137(1):259-286. https://doi.org/10.1007/s11277-024-11401-y.
• [19] Liu S, Yu S, Li H, Yang Z, Duan M, Liao X. A novel shilling attack on black-box recommendation systems for multiple targets. Neural Computing and Applications, 2024;37(5):3399-3417. https://doi.org/10.1007/s00521-024-10798-8.
• [20] Gunes I, Kaleli C, Bilge A, Polat H. Shilling attacks against recommender systems: a comprehensive survey. Artificial Intelligence Review, 2012;42(4):767-799. https://doi.org/10.1007/s10462-012-9364-9.
• [21] Güneş İ. Robustness Analysis of a novel Model-Based Recommendation Algorithms in Privacy Environment. KSII Transactions on Internet and Information Systems, 2024;18(5). https://doi.org/10.3837/tiis.2024.05.011.
• [22] Bobadilla J, Ortega F, Hernando A, Alcalá J. Improving collaborative filtering recommender system results and performance using genetic algorithms. Knowledge-Based Systems, 2011;24(8):1310-1316. https://doi.org/10.1016/j.knosys.2011.06.005.
• [23] Ar Y, Bostanci E. A genetic algorithm solution to the collaborative filtering problem. Expert Systems With Applications, 2016; 61:122-128. https://doi.org/10.1016/j.eswa.2016.05.021.
• [24] Abdolmaleki A, Rezvani MH. An optimal context-aware content-based movie recommender system using genetic algorithm: a case study on MovieLens dataset. Journal of Experimental & Theoretical Artificial Intelligence, 2022;36(8):1485-1511. https://doi.org/10.1080/0952813x.2022.2153279.
• [25] Dao TH, Jeong SR, Ahn H. A novel recommendation model of location-based advertising: Context-Aware Collaborative Filtering using GA approach. Expert Systems With Applications, 2011;39(3):3731-3739. https://doi.org/10.1016/j.eswa.2011.09.070.
• [26] Holland JH. Adaptation in natural and artificial systems. Ann Arbor, MI, USA: University of Michigan Press, 1975.
• [27] Golberg DE. Genetic algorithms in search, optimization, and machine learning. Addion wesley, 1989(102):36.
• [28] Mitchell M. An Introduction to Genetic Algorithms. MIT press; 1998.
• [29] Bhaumik R, Williams C, Mobasher B, Burke R. Securing collaborative filtering against malicious attacks through anomaly detection. In: Proceedings of the 4th Workshop on Intelligent Techniques for Web Personalization (ITWP’06), Boston, Vol 6. 2006:10.
• [30] Lam SK, Riedl J. Shilling recommender systems for fun and profit. In: Proceedings of the 13th International Conference on World Wide Web, 2004:393-402.
• [31] Gunes I, Bilge A, Polat H. Shilling attacks against Memory-Based Privacy-Preserving recommendation algorithms. KSII Transactions on Internet and Information Systems, 2013;7(5):1272-1290. https://doi.org/10.3837/tiis.2013.05.019.
• [32] Zhou W, Wen J, Qu Q, Zeng J, Cheng T. Shilling attack detection for recommender systems based on credibility of group users and rating time series. PLoS ONE, 2018;13(5):e0196533. https://doi.org/10.1371/journal.pone.0196533.