Şilin Ataklarının Tek Sınıflı Destek Vektör Makinaları ile Tespiti

Year 2023, Volume: 5 Issue: 2, 246 - 256, 31.12.2023

Halil İbrahim Ayaz , Zehra Kamışlı Öztürk

https://doi.org/10.47112/neufmbd.2023.22

Abstract

Öneri sistemleri çeşitli çevrimiçi platformlarda hayati bir rol oynar ve kullanıcıların tercihlerini göz önünde bulundurarak yeni ürünler, hizmetler ve içerikler keşfetmelerine yardımcı olur. Bununla birlikte, bu sistemler, kötü niyetli kullanıcıların derecelendirmeleri yapay olarak şişirdiği veya söndürdüğü ve önyargılı önerilere yol açtığı şilin saldırıları yoluyla manipülasyona karşı savunmasızdır. Bu saldırıları araştırmanın, anlamanın ve hafifletmenin önemini vurgulamak çok önemlidir. Bu tür saldırıları tespit etmek, tavsiye sistemlerinin bütünlüğünü ve etkinliğini korumak için çok önemlidir. Literatürde, şilin saldırılarını tespit etmek için birçok çalışma sunulmuştur. En iyi bilinen kümeleme yöntemleri farklı saldırı modelleri için uyarlanmıştır. Bu makalede, şilin saldırılarını tespit etmek için gürbüz bir teknik olarak Tek Sınıflı Destek Vektör Makineleri kullanımını araştırıyoruz. Tek Sınıflı Destek Vektör Makinaları, öncelikle anomali tespiti ve aykırılık tespiti görevleri için tasarlanmış geleneksel Destek Vektör Makinelerinin özel bir çeşididir. Önerilen yöntemi doğrulamak için MovieLens100K veri kümesi kullanılmıştır. Sonuç olarak, farklı boyut ve doluluk oranlı saldırılar için hassasiyet ve geri çağırma değerleri verilmiştir.

Keywords

Öneri sistemleri, Şilin atakları, Tek sınıflı destek vektör makinaları

Supporting Institution

Eskişehir Teknik Üniversitesi

Project Number

20DRP026

Shilling Attack Detection with One Class Support Vector Machines

Abstract

Recommender systems play a vital role in various online platforms, assisting users in discovering new products, services, and content considering their preferences. However, these systems are vulnerable to manipulation through shilling attacks, where malicious users artificially inflate or deflate ratings, leading to biased recommendations. It is crucial to emphasize the importance of researching, understanding, and mitigating these attacks. Detecting such attacks is crucial to maintaining the integrity and effectiveness of recommender systems. In the literature, lots of studies are presented to detect shilling attacks. The most well-known clustering methods are adapted for different attack models. This paper explores using One-Class Support Vector Machines (OCSVM) as a robust technique for detecting shilling attacks. One-Class SVMs are a specialized variant of the traditional Support Vector Machines, primarily designed for anomaly and novelty detection tasks. MovieLens100K dataset is used to validate the proposed method. As a result, precision and recall values are given for different attack and filler sizes.

Keywords

Recommender systems, Shilling attacks, OCSVM

Project Number

20DRP026

References

• Y. Ge, S. Zhao, H. Zhou, C. Pei, F. Sun, W. Ou, Y. Zhang, Understanding Echo Chambers in E-commerce Recommender Systems, SIGIR 2020 - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, Inc, Rutgers University, Piscataway, United States, 2020: ss. 2261-2270. doi:10.1145/3397271.3401431.
• R.M. Frey, D. Vučkovac, A. Ilic, A secure shopping experience based on blockchain and beacon technology, içinde: G. I., S. A. (Ed.), CEUR Workshop Proceedings, CEUR-WS, ETH Zurich, Weinbergstrasse 56/58, Zurich, 8092, Switzerland, 2016.
• Y. Han, Z. Han, J. Wu, Y. Yu, S. Gao, D. Hua, A. Yang, Artificial Intelligence Recommendation System of Cancer Rehabilitation Scheme Based on IoT Technology, IEEE Access. 8 (2020), 44924-44935. doi:10.1109/ACCESS.2020.2978078.
• C.C. Yang, L. Jiang, Enriching User Experience in Online Health Communities Through Thread Recommendations and Heterogeneous Information Network Mining, IEEE Transactions on Computational Social Systems. 5 (2018), 1049-1060. doi:10.1109/TCSS.2018.2879044.
• A. Alsalemi, Y. Himeur, F. Bensaali, abbes amira, C. Sardianos, I. Varlamis, G. Dimitrakopoulos, achieving Domestic Energy Efficiency Using Micro-Moments and Intelligent Recommendations, IEEE Access. 8 (2020), 15047-15055. doi:10.1109/aCCESS.2020.2966640.
• C. Sardianos, I. Varlamis, G. Dimitrakopoulos, D. Anagnostopoulos, A. Alsalemi, F. Bensaali, Y. Himeur, A. Amira, REHAB-C: Recommendations for Energy HABits Change, Future Generation Computer Systems. 112 (2020), 394-407. doi:10.1016/j.future.2020.05.041.
• Q. Li, J. Kim, A deep learning-based course recommender system for sustainable development in education, Applied Sciences (Switzerland). 11 (2021). doi:10.3390/app11198993.
• P. V. Kulkarni, S. Rai, R. Kale, Recommender System in eLearning: A Survey, Proceeding of International Conference on Computational Science and Applications. (2020), 119-126. doi:10.1007/978-981-15-0790-8_13.
• S. Puglisi, J. Parra-Arnau, J. Forné, D. Rebollo-Monedero, On content-based recommendation and user privacy in social-tagging systems, Computer Standards and Interfaces. 41 (2015), 17-27. doi:10.1016/j.csi.2015.01.004.
• A. Bilge, Z. Ozdemir, H. Polat, A novel shilling attack detection method, Procedia Computer Science, 31 (2014), 165-174. doi:10.1016/j.procs.2014.05.257.
• M. Si, Q. Li, Shilling attacks against collaborative recommender systems: a review, Artificial Intelligence Review. 53 (2020), 291-319. doi:10.1007/s10462-018-9655-x.
• F. Rezaimehr, C. Dadkhah, A survey of attack detection approaches in collaborative filtering recommender systems, Artificial Intelligence Review. 54 (2021), 2011-2066. doi:10.1007/s10462-020-09898-3.
• Z. Batmaz, B. Yilmazel, C. Kaleli, Shilling attack detection in binary data: a classification approach, Journal of Ambient Intelligence and Humanized Computing. 11 (2020), 2601-2611. doi:10.1007/s12652-019-01321-2.
• F. Zhang, Q. Zhou, HHT-SVM: An online method for detecting profile injection attacks in collaborative recommender systems, Knowledge-Based Systems. 65 (2014), 96-105. doi:10.1016/j.knosys.2014.04.020.
• S. Zahra, M.A. Ghazanfar, A. Khalid, M.A. Azam, U. Naeem, A. Prugel-Bennett, Novel centroid selection approaches for KMeans-clustering based recommender systems, Information Sciences. 320 (2015), 156-189. doi:10.1016/j.ins.2015.03.062.
• F. Zhang, S. Wang, Detecting Group Shilling Attacks in Online Recommender Systems Based on Bisecting K-Means Clustering, IEEE Transactions on Computational Social Systems. 7 (2020), 1189-1199. doi:10.1109/TCSS.2020.3013878.
• R. Bhaumik, B. Mobasher, R. Burke, A Clustering Approach to Unsupervised Attack Detection in Collaborative Recommender Systems, Proceedings of the 7th IEEE international conference on data mining. (2011), 181-187.
• R. Bhaumik, C. Williams, B. Mobasher, R. Burke, Securing collaborative filtering against malicious attacks through anomaly detection, AAAI Workshop - Technical Report. WS-06-10 (2006), 50-59.
• Z. Wu, J. Wu, J. Cao, D. Tao, HySAD: A semi-supervised hybrid shilling attack detector for trustworthy product recommendation, içinde: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2012: ss. 985-993. doi:10.1145/2339530.2339684.
• Z. Yang, Z. Cai, X. Guan, Estimating user behavior toward detecting anomalous ratings in rating systems, Knowledge-Based Systems. 111 (2016), 144-158. doi:10.1016/j.knosys.2016.08.011.
• B. Mobasher, R. Burke, R. Bhaumik, J.J. Sandvig, Attacks and remedies in collaborative recommendation, IEEE Intelligent Systems. 22(3) (2007), 56-63. doi:10.1109/MIS.2007.45.
• S.K. Lam, J. Riedl, Shilling recommender systems for fun and profit, içinde: Thirteenth International World Wide Web Conference Proceedings, WWW2004, Association for Computing Machinery, GroupLens Research, Computer Science and Engineering, University of Minnesota, Minneapolis, MN 55455, United States, 2004: ss. 393-402. doi:10.1145/988672.988726.
• R. Burke, B. Mobasher, R. Zabicki, Runa. Bhaumik, Identifying Attack Models for Secure Recommendation, Beyond Personalization. (2005), 19-25.
• B. Mobasher, R. Burke, R. Bhaumik, C. Williams, Effective Attack Models for Shilling Item-Based Collaborative Filtering System, WEBKDD. 2005, (2005).
• M.P. O’Mahony, N.J. Hurley, G.C.M. Silvestre, Recommender systems: Attack types and strategies, içinde: Proceedings of the National Conference on Artificial Intelligence, 2005: ss. 334-339.
• C. Williams, B. Mobasher, Thesis: Profile Injection Attack Detection for Securing Collaborative Recommender Systems, (2006), 1-47.
• A. Pektaş, O. İnan, Ağaç Tohum Algoritmasının Kümeleme Problemlerine Uygulanması, Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi. 4 (2022), 1-10. doi:10.47112/neufmbd.2022.8.
• F. Zhang, Z. Zhang, P. Zhang, S. Wang, UD-HMM: An unsupervised method for shilling attack detection based on hidden Markov model and hierarchical clustering, Knowledge-Based Systems. 148 (2018), 146-166. doi:10.1016/j.knosys.2018.02.032.
• H. Cai, F. Zhang, An unsupervised method for detecting shilling attacks in recommender systems by mining item relationship and identifying target items, Computer Journal. 62 (2019), 579-597. doi:10.1093/comjnl/bxy124.
• L. Yang, W. Huang, X. Niu, Defending shilling attacks in recommender systems using soft co-clustering, IET Information Security. 11 (2017), 319-325. doi:10.1049/iet-ifs.2016.0345.
• A. Davoudi, M. Chatterjee, Detection of profile injection attacks in social recommender systems using outlier analysis, Proceedings - 2017 IEEE International Conference on Big Data, Big Data 2017. 2018-Janua (2017), 2714-2719. doi:10.1109/BigData.2017.8258235.
• C. Panagiotakis, H. Papadakis, P. Fragopoulou, Unsupervised and supervised methods for the detection of hurriedly created profiles in recommender systems, International Journal of Machine Learning and Cybernetics. 11 (2020), 2165-2179. doi:10.1007/s13042-020-01108-4.
• J.M. Alostad, Improving the Shilling Attack Detection in Recommender Systems Using an SVM Gaussian Mixture Model, Journal of Information and Knowledge Management. 18(01) (2019). doi:10.1142/S0219649219500114.
• L. Zhang, Y. Yuan, Z. Wu, J. Cao, Semi-SGD: Semi-Supervised Learning Based Spammer Group Detection in Product Reviews, Proceedings - 5th International Conference on Advanced Cloud and Big Data, CBD 2017. 2017, 368-373. doi:10.1109/CBD.2017.70.
• Q. Zhou, L. Duan, Semi-supervised recommendation attack detection based on Co-Forest, Computers and Security. 109 (2021), 102390. doi:10.1016/j.cose.2021.102390.
• Y. Wang, R. Zhang, N. Masoud, H.X. Liu, Anomaly detection and string stability analysis in connected automated vehicular platoons, Transportation Research Part C: Emerging Technologies. 151 (2023), 104114. doi:10.1016/j.trc.2023.104114.
• C. Li, L. Mo, H. Tang, R. Yan, Lifelong condition monitoring based on NB-IoT for anomaly detection of machinery equipment, Procedia Manufacturing. 49 (2020), 144-149. doi:10.1016/j.promfg.2020.07.010.
• C. Cao, M. Liu, B. Li, Y. Wang, Mechanical fault diagnosis of high voltage circuit breakers utilizing VMD based on improved time segment energy entropy and a new hybrid classifier, IEEE Access. 8 (2020), 177767-177781. doi:10.1109/ACCESS.2020.3027478.
• A. Karasmanoglou, M. Antonakakis, M. Zervakis, ECG-Based Semi-Supervised Anomaly Detection for Early Detection and Monitoring of Epileptic Seizures, International Journal of Environmental Research and Public Health. 20 (2023), 5000. doi:10.3390/ijerph20065000.
• A.A. Abdulhussein, M.F. Nasrudin, S.M. Darwish, Z.A.A. Alyasseri, A Genetic Algorithm Based One Class Support Vector Machine Model for Arabic Skilled Forgery Signature Verification, Journal of Imaging. 9 (2023). doi:10.2139/ssrn.4303232.
• T. Cheng, A. Dairi, F. Harrou, Y. Sun, T. Leiknes, Monitoring influent conditions of wastewater treatment plants by nonlinear data-based techniques, IEEE Access. 7 (2019), 108827-108837. doi:10.1109/ACCESS.2019.2933616.
• M. Karakoyun, A. Özkış, Transfer Fonksiyonları Kullanarak İkili Güve-Alev Optimizasyonu Algoritmalarının Geliştirilmesi ve Performanslarının Karşılaştırılması, Necmettin Erbakan Üniversitesi Fen ve Mühendislik Bilimleri Dergisi. 3 (2021), 1-10.
• M. Erişoğlu, N. Yaman, Ridge Tahminine Dayalı Kantil Regresyon Analizinde Yanlılık Parametresi Tahminlerinin Performanslarının Karşılaştırılması, Necmettin Erbakan University Journal of Science and Engineering. 1 (2019), 103-111.
• Y. Guerbai, Y. Chibani, Y. Meraihi, Techniques for Selecting the Optimal Parameters of One-Class Support Vector Machine Classifier for Reduced Samples, International Journal of Applied Metaheuristic Computing. 13 (2021,) 1-15. doi:10.4018/ijamc.290533.
• S. Wang, Q. Liu, E. Zhu, F. Porikli, J. Yin, Hyperparameter selection of one-class support vector machine by self-adaptive data shifting, Pattern Recognition. 74 (2018) 198-211. doi:10.1016/j.patcog.2017.09.012.
• Z. Ghafoori, S.M. Erfani, S. Rajasegarar, J.C. Bezdek, S. Karunasekera, C. Leckie, Efficient Unsupervised Parameter Estimation for One-Class Support Vector Machines, IEEE Transactions on Neural Networks and Learning Systems. 29 (2018), 5057-5070. doi:10.1109/TNNLS.2017.2785792.
• S. Wang, Q. Liu, E. Zhu, J. Yin, W. Zhao, MST-GEN: An Efficient Parameter Selection Method for One-Class Extreme Learning Machine, IEEE Transactions on Cybernetics. 47 (2017), 3266-3279. doi:10.1109/TCYB.2017.2707463.
• A. Anaissi, A. Braytee, M. Naji, Gaussian Kernel Parameter Optimization in One-Class Support Vector Machines, Proceedings of the International Joint Conference on Neural Networks. 2018, doi:10.1109/IJCNN.2018.8489383.
• Y. Xiao, H. Wang, W. Xu, Parameter selection of gaussian kernel for one-class SVM, IEEE Transactions on Cybernetics. 45 (2015), 941-953. doi:10.1109/TCYB.2014.2340433.