跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 鍾瑞益
Jui-Yi Chung
論文名稱： Using the Beta Distribution Technique to Detect Attacked Items of Collaborative Filtering
指導教授： 許秉瑜
口試委員:
學位類別： 博士
Doctor
系所名稱： 管理學院 - 企業管理學系
Department of Business Administration
論文出版年： 2021
畢業學年度： 109
語文別： 英文
論文頁數： 53
中文關鍵詞： 推薦系統 、beta 分佈 、托攻擊 、推升攻擊 、打壓攻擊
外文關鍵詞： Shilling Attacks, Recommendation Systems, Beta Distribution, Push Attack, Nuke Attack
相關次數： 點閱：10  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 推薦系統基於使用者和商品項目，向使用者提供適當的商品項目並有效地幫助使用 者找到可能感興趣的商品。而最常用的推薦方法是協作過濾。然而，在某些情況下，由於推薦系統的開放特性，導致推薦系統會被有心人士注入虛假的評分數據資料以便創造出虛 假的等級來推升或降低特定商品的評分，影響到推薦清單的產出。這樣的結果，事實上會 影響到使用者對推薦系統的信任。畢竟，推薦系統提供可信任的推薦商品清單是很重要。

    儘管先前已經有針對攻擊檢測相關的研究提出，但是大多數主要是利用以用戶為導 向的攻擊檢測，將惡意用戶進行檢測和刪除。過去也有關注檢測受攻擊項目的研究。其中有研究所使用的方法需要密集的 user-item matrix，並透過一些已知的標準先將項目進行分組。本研究基於協作過濾的推薦系統其所使用的 user-item matrix 資料，在沒有先前的那些限制下，利用 Beta Distribution 的方法來檢測受攻擊的項目。其實驗結果表明，整個模擬攻 擊的檢測率大於 80%，錯殺率小於 16%。

    A recommender system providing appropriate items to the user, effectively helping them to find items that may be of interest. The most common recommendation method is collaborative filtering. However, these recommender systems can be injected with false data to create false ratings to push or nuke specific items. This will greatly affect the user trust in the recommender system. After all, it is important that the recommender system recommends a trusted item.

    Although previous studies have investigated how to detect attacks, most focus on user-orientation detection, i.e., detect and remove malicious users. To our best knowledge, only a few previous studies have considered how to detect items under attacks. However, one of the proposed methods requires a dense user-item matrix and clustering items into groups based on some known criteria. Therefore, this study proposes detecting items under attack without these constraints, using beta distribution with the user-item matrix utilized with the collaborative filtering recommender system. Experimental results show that the detection rate of the simulated attack is more than 80%, and the false rate is less than 16%.

    Table of Contents Pages Chinese Abstract......................i English Abstract...........................ii Table of Contents.........................iii List of Figures.............................v List of Tables.............................vi Chapter I Introduction......................1 1-1 Background..............................1 1-2 Motivation..............................2 1-3 Research Gap............................2 1-4 Research Contribution...................3 1-5 Overview of The Paper...................4 Chapter II Literature Review................5 2-1 Recommender System......................5 2-2 Modes of Shilling Attack................7 2-3 Detection Method.......................11 Chapter III Proposed Methodology...........13 3-1 Beta Distribution......................13 3-2 Converting User–Item Matrix to Positive and Negative Matrices...................................16 3-3 Detecting Exceptional Items with Beta Distributions... ...........................................19 3-4 Identifying Attacked Items Using Combinations of Various Beta Distributions.........................21 3-5 Quality Measurement....................24 Chapter IV Experimental Evaluation.........25 4-1 Data Description.......................25 4-2 Attack Simulation......................25 4-3 Finding Quantile.......................26 4-4 Experimental Results...................27 4-5 Performance Robust.....................32 4-6 Performance Comparison.................35 Chapter V Conclusion and Feature Work......38 5-1 Conclusion.............................38 5-2 Feature Work...........................39 Bibliography...............................40

    Bibliography
    [1] A. Bilge, Z. Ozdemir, and H. Polat, “A novel shilling attack detection method”, Procedia Computer Science, Vol 31, 2014, pp.165-174.
    [2] Amazon Files Suit against Individuals Offering Fake Product Reviews on Fiverr.com, Retrieved from https://techcrunch.com/2015/10/16/amazon-files-suit-against-individuals- offering-fake-product-reviews-on-fiverr-com/, 2015.
    [3] A. Jøsang and R. Ismail, “The beta reputation system”, In Proceedings of the 15th Bled Conference on Electronic Commerce Conference, Bled, Slovenia, 2002.
    [4] A. Whitrby, A. Jøsang and J. Indulska,“Filtering out unfair ratings in Bayesian reputation
    system”, In Proceedings of the Third International Joint Conference on Autonomous Agents
    and Multi Agent Systems, 2004.
    [5] B. Mehta, T. Hofmann and P. Fankhauser, “Lies and propaganda: Detecting spam users in collaborative filtering”, In Proceedings of the 12th International Conference on Intelligent User Interfaces, Honolulu Hi USA, 2007.
    [6] B. Mehta, “Unsupervised shilling detection for collaborative filtering”, In Proceedings of the 22nd National Conference on Artificial Intelligence, British Columbia Canada, 2007.
    [7] B. Mehta and W. Nejdl, “Unsupervised strategies for shilling detection and robust collaborative filtering”, User Modeling and User-Adapted Interaction, Vol 19, 2009, pp.65- 97.
    [8] B. Mobasher, “Secure personalization: Building trustworthy recommender system”, In 10th DELOS Thematic Workshop on Personalized Access, Profile Management, and Context Awareness in Digital Libraries, Corfu Greece, 2007.
    [9] B. Mobasher, R. Burke, R. Bhaumik and C. Williams, “Towards trustworthy recommender systems: an analysis of attack models and algorithm robustness”, ACM Transactions on Internet Technology, Vol 7(4), 2007, pp.23-38.
    [10] B. Mobasher, R. Burke, R. Bhaumik and J.J. Sandvig, “Attacks and remedies in collaborative recommendation”, IEEE Intelligent System, Vol 22(3), 2007, pp.56-63.
    40
    [11] B. Sun, X. Luo, M. Akiyama, T. Watanabe, and T. Mori, “PADetective: A systematic approach to automate detection of promotional attackers in mobile app store”, Journal of Information Processing, Vol. 26, 2018, pp.212-223.
    [12] C.A. Williams, B. Mobasher, and R. Burke, “Defending recommender systems detection of profile injection attacks”, Service Oriented Computing and Applications, Vol 1, 2007, pp.157- 170.
    [13] C.C. Aggarwal, Recommender systems – The textbook, Springer, 2016
    [14] C. Li and Z. Luo, “A hybrid item-based recommendation algorithm against segment attack in collaborative filtering systems”, In 2011 International Conference on Information Management, Innovation Management and Industrial Engineering, Shenzhen, China. 2011.
    [15] C. Williams, B. Mobasher, R. Burke, J. Sandvig and R. Bhaumik, “Detection of obfuscated attacks in collaborative recommender systems”, In ECAI'06 Proceedings of the 17th European Conference on Artificial Intelligence, Riva del Garda Italy, 2006.
    [16] C.Y. Chung, P.Y. Hsu and S.H. Huang, “βP: A novel approach to filter out malicious rating profiles from recommender systems”, Decision Support Systems, Vol 55, 2013, pp.314-325.
    [17] Data Science Movies Recommendation System, Retrieved from
    https://www.datasciencecentral.com/profiles/blogs/data-science-movies-recommendation- system, 2020.
    [18] D. Ramalingam and V. Chinnaiah, “Fake profile detection techniques in large-scale online social networks: A comprehensive review”, Computers and Electrical Engineering, Vol 65, 2017, pp.165-177.
    [19] E. Lim, V.-A. Nguyen, N. Jindal, B. Liu and H. Lauw, “Detecting product review spammers using rating behaviors”, In Proceedings of the 19th ACM International Conference on Information and Knowledge Management CIKM ’10, Toronto Canada, 2010.
    nd
    [20] F.Ricci, L.Rokach and B.Shapira, Recommender systems Handbook 2
    , Springer, 2015
    [21] F. Zhang, Z. Ling and S. Wang, “Unsupervised approach for detecting shilling attacks in collaborative recommender systems based on user rating behaviours”, IET Information Security, Vol 13(3), 2019, pp.174-187.
    41

    [22] GroupLens Lab, MovieLens Dataset, https://grouplens.org/datasets/movielens/ accessed 15 January 2019.
    [23] H. Yu and F. Zhang, “Collaborative filtering recommender system in adversarial environment”, In Proceedings of the 2012 International Conference on Machine Learning and Cybernetics, Xian China, 2012.
    [24] I. Gunes, C. Kaleli, A. Bilge and H. Polat, “Shilling attacks against recommender systems: A comprehensive survey”, Artificial Intelligence Review, Vol 42, 2012, pp.767-799.
    [25] It’s about ethics in user reviews – how to get a positive Steam critique of your game for $5, Retrieved from http://www.pcgamesn.com/its-about-ethics-in-user-reviews-how-to-get-a- positive-steam-critique-for-$5, 2016.
    [26] J. Zou, and F. Fekri, “A belief propagation approach of detecting smiling attacks in collaborative filtering”, In CIKM’13 Proceedings of the 22nd ACM international conference on information & knowledge management, 2013.
    [27] Long tail, WiKi, Retrieved from https://en.wikipedia.org/wiki/Long_tail, 2020.
    [28] Long tail, Wired,Retrieved from https://www.wired.com/2004/10/tail/, 2004.
    [29] L. Yang, W. Huang and X. Niu, “Defending shilling attacks in recommender systems using soft co-clustering”, IEF Information Security, Vol 11(6), 2017, pp.319-325.
    [30] M. Gao, B. Ling, Q. Yuan, Q. Xiong, and L. Yang, “A robust collaborative filtering approach based on user relationships for recommendation systems”, Mathematical Problems in Engineering, Vol 1, 2014, pp.1-8.
    [31] M.J. Pazzani, “A framework for collaborative, content-based and demographic filtering”, Artificial Intelligence Review, Vol 13(5-6), 1999, pp.393-408.
    [32] M.P. O’Mahony, N.J. Hurley and G.C.M. Silvestre, “Collaborative filtering - safe and sound?”, Foundations of Intelligent Systems, Vol 2871, 2003, pp.506-510.
    [33] N. Hurley, Z. Cheng and M. Zhang, “Statistical attack detection”, In Proceedings of the Third ACM Conference on Recommender Systems, ACM Press, 2009.
    [34] P. Johnson and M. Beverlin, Beta Distribution, 2013.
    42

    [35] P. Resnick and H. Varian, “Recommender systems”, Communications of the ACM, Vol 40(3), 1997.
    [36] R. Balani, “Role of e-commerce in changing business environment”, International Journal of Advanced Research in Commerce, Management & Social Science, Vol 02(3), 2019, pp.109- 112.
    [37] R. Burke, “Hybrid Recommender systems: survey and experiments”, User Modeling and User-Adapted Interaction, Vol 12(4), 2002.
    [38] R. Bhaumik, C. Williams, B. Mobasher and R. Burke, “Securing collaborative filtering against malicious attacks through anomaly detection”, In Proceedings of the 4th Workshop on Intelligent Techniques for Web Personalization, Boston, MA, 2006.
    [39] R. Burke, B. Mobasher, C. Williams and R, Bhaumik, “Classification features for attack detection in collaborative recommender systems”, KDD '06 Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM Press, 2006.
    [40] R. K. Dewang and A. K. Singh, “State-of-art approaches for review spammer detection: A survey”, Journal of Intelligent Information Systems, Vol 50(2), 2018, pp.231-264.
    [41] S. Lam and J. Riedl, “Shilling recommender systems for fun and profit”, Proc. Int. Conf. World Wide Web WWW’04, 2004, pp.393–402.
    [42] W. Zhou, J. Wen, Y.S. Koh, S. Alam, and G. Dobbie, “Attack detection in recommender systems based on target item analysis”, 2014 International Joint Conference on Neural Networks (IJCNN), 2014, pp.332-339.
    [43] X. Luo, Y. Xia and O. Zhu, “Incremental collaborative filtering recommender based on regularized matrix factorization”, Knowledge-Based Systems, Vol 27, 2012, pp.271-280.
    [44] X. Su and T.M. Khoshgoftaar, “A survey of collaborative filtering techniques”, Advances in Artificial Intelligence, Vol 2009, 2009, 19 pages.

    QR CODE
    :::