Defending recommender systems by influence analysis

Collaborative filtering (CF) is a popular method for personalizing product recommendations for e-commerce applications. In order to recommend a product to a user and predict that user’s preference, CF utilizes product evaluation ratings of like-minded users. The process of finding like-minded users forms a social network among all users and each link between two users represents an implicit connection between them. Users having more connections with others are the most influential users. Attacking recommender systems is a new issue for these systems. Here, an attacker tries to manipulate a recommender system in order to change the recommendation output according to her wish. If an attacker succeeds, her profile is used over and over again by the recommender system, making her an influential user. In this study, we applied the established attack detection methods to the influential users, instead of the whole user set, to improve their attack detection performance. Experiments were conducted using the same settings previously used to test the established methods. The results showed that the proposed influence-based method had better detection performance and improved the stability of a recommender system for most attack scenarios. It performed considerably better than established detection methods for attacks that inserted low numbers of attack profiles (20–25 %).

[1]  John Riedl,et al.  Shilling recommender systems for fun and profit , 2004, WWW '04.

[2]  Mehdi Shajari,et al.  Who are the most influential users in a recommender system? , 2011, ICEC '11.

[3]  Xiaohui Liu,et al.  Editorial: Data mining for understanding user needs , 2010, TCHI.

[4]  Shyhtsun Felix Wu,et al.  Social Manipulation of Online Recommender Systems , 2010, SocInfo.

[5]  Neil J. Hurley,et al.  Collaborative recommendation: A robustness analysis , 2004, TOIT.

[6]  Paolo Avesani,et al.  Trust-aware recommender systems , 2007, RecSys '07.

[7]  Michael J. Shaw,et al.  Application of Decision-Tree Induction Techniques to Personalized Advertisements on Internet Storefronts , 2001, Int. J. Electron. Commer..

[8]  Paolo Avesani,et al.  A trust-enhanced recommender system application: Moleskiing , 2005, SAC '05.

[9]  Wolfgang Nejdl,et al.  Preventing shilling attacks in online recommender systems , 2005, WIDM '05.

[10]  Gediminas Adomavicius,et al.  On the stability of recommendation algorithms , 2010, RecSys '10.

[11]  Fuguo Zhang.  Analysis of Love-Hate Shilling Attack Against E-commerce Recommender System , 2010, 2010 International Conference of Information Science and Management Engineering.

[12]  Qinghua Hu,et al.  Dynamic time warping constraint learning for large margin nearest neighbor classification , 2011, Inf. Sci..

[13]  Hyung Jun Ahn,et al.  Selecting a small number of products for effective user profiling in collaborative filtering , 2010, Expert Syst. Appl..

[14]  John Riedl,et al.  Mining influence in recommender systems , 2007 .

[15]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[16]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[17]  John C. S. Lui,et al.  Friends or Foes: Detecting Dishonest Recommenders in Online Social Networks , 2011, 2011 Proceedings of 20th International Conference on Computer Communications and Networks (ICCCN).

[18]  Yanlong Zhai,et al.  The design and implementation of service process reconfiguration with end-to-end QoS constraints in SOA , 2010, Service Oriented Computing and Applications.

[19]  Sung Jin Hur,et al.  Improved trust-aware recommender system using small-worldness of trust networks , 2010, Knowl. Based Syst..

[20]  Fuguo Zhang.  Average Shilling Attack against Trust-Based Recommender Systems , 2009, 2009 International Conference on Information Management, Innovation Management and Industrial Engineering.

[21]  Sakti Pramanik,et al.  Efficient k-nearest neighbor searching in nonordered discrete data spaces , 2010, TOIS.

[22]  Vincent S. Tseng,et al.  Personalized rough-set-based recommendation by integrating multiple contents and collaborative information , 2010, Inf. Sci..

[23]  Duen-Ren Liu,et al.  A hybrid of sequential rules and collaborative filtering for product recommendation , 2009, Inf. Sci..

[24]  Bamshad Mobasher,et al.  Defending recommender systems: detection of profile injection attacks , 2007, Service Oriented Computing and Applications.

[25]  Martin Ester,et al.  A matrix factorization technique with trust propagation for recommendation in social networks , 2010, RecSys '10.

[26]  R. Burke,et al.  Limited Knowledge Shilling Attacks in Collaborative Filtering Systems , 2005 .

[27]  Padraig Cunningham,et al.  Unsupervised retrieval of attack profiles in collaborative recommender systems , 2008, RecSys '08.

[28]  John Riedl,et al.  Influence in Ratings-Based Recommender Systems: An Algorithm-Independent Approach , 2005, SDM.

[29]  Jia Wang,et al.  User comments for news recommendation in forum-based social media , 2010, Inf. Sci..

[30]  Bamshad Mobasher,et al.  Robustness of collaborative recommendation based on association rule mining , 2007, RecSys '07.

[31]  Bamshad Mobasher,et al.  Classification features for attack detection in collaborative recommender systems , 2006, KDD '06.

[32]  Susan T. Dumais,et al.  Potential for personalization , 2010, TCHI.

[33]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[34]  Hong Joo Lee,et al.  Use of social network information to enhance collaborative filtering performance , 2010, Expert Syst. Appl..

[35]  John Riedl,et al.  Learning preferences of new users in recommender systems: an information theoretic approach , 2008, SKDD.

[36]  Martin Ester,et al.  TrustWalker: a random walk model for combining trust-based and item-based recommendation , 2009, KDD.

[37]  Johanna D. Moore,et al.  Evaluating information presentation strategies for spoken recommendations , 2007, RecSys '07.

[38]  Bamshad Mobasher,et al.  Analysis and Detection of Segment-Focused Attacks Against Collaborative Recommendation , 2005, WEBKDD.

[39]  John Riedl,et al.  An algorithmic framework for performing collaborative filtering , 1999, SIGIR '99.

[40]  Ramayya Krishnan,et al.  Internet content filtering using isotonic separation on content category ratings , 2007, TOIT.

[41]  Bamshad Mobasher,et al.  Towards Trustworthy Recommender Systems : An Analysis of Attack Models and Algorithm Robustness , 2007 .