Shilling attack detection for recommender systems based on credibility of group users and rating time series

Recommender systems are vulnerable to shilling attacks. Forged user-generated content data, such as user ratings and reviews, are used by attackers to manipulate recommendation rankings. Shilling attack detection in recommender systems is of great significance to maintain the fairness and sustainability of recommender systems. The current studies have problems in terms of the poor universality of algorithms, difficulty in selection of user profile attributes, and lack of an optimization mechanism. In this paper, a shilling behaviour detection structure based on abnormal group user findings and rating time series analysis is proposed. This paper adds to the current understanding in the field by studying the credibility evaluation model in-depth based on the rating prediction model to derive proximity-based predictions. A method for detecting suspicious ratings based on suspicious time windows and target item analysis is proposed. Suspicious rating time segments are determined by constructing a time series, and data streams of the rating items are examined and suspicious rating segments are checked. To analyse features of shilling attacks by a group user’s credibility, an abnormal group user discovery method based on time series and time window is proposed. Standard testing datasets are used to verify the effect of the proposed method.

[1]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[2]  Shi-Jinn Horng,et al.  A novel intrusion detection system based on hierarchical clustering and support vector machines , 2011, Expert Syst. Appl..

[3]  Xiuzhen Zhang,et al.  A probabilistic method for emerging topic tracking in Microblog stream , 2016, World Wide Web.

[4]  Fillia Makedon,et al.  Analysis of a low-dimensional linear model under recommendation attacks , 2006, SIGIR.

[5]  Gillian Dobbie,et al.  Attack detection in recommender systems based on target item analysis , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[6]  Ji Zhang,et al.  On Efficient and Robust Anonymization for Privacy Protection on Massive Streaming Categorical Information , 2017, IEEE Transactions on Dependable and Secure Computing.

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

[8]  Junjie Wu,et al.  HySAD: a semi-supervised hybrid shilling attack detector for trustworthy product recommendation , 2012, KDD.

[9]  Junhao Wen,et al.  SVM-TIA a shilling attack detection method based on SVM and target item analysis in recommender systems , 2016, Neurocomputing.

[10]  Schubert Foo,et al.  Collaborative Querying through a Hybrid Query Clustering Approach , 2003, ICADL.

[11]  Robin Burke,et al.  Securing collaborative filtering against malicious attacks through anomaly detection , 2006, AAAI 2006.

[12]  Ingoo Han,et al.  Detection of the customer time-variant pattern for improving recommender systems , 2005, Expert Syst. Appl..

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

[14]  Jiankun Hu,et al.  A novel statistical technique for intrusion detection systems , 2018, Future Gener. Comput. Syst..

[15]  Robin Burke,et al.  Effective Attack Models for Shilling Item-Based Collaborative Filtering Systems , 2005 .

[16]  Zunping Cheng,et al.  Statistical attack detection , 2009, RecSys '09.

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

[18]  Bamshad Mobasher,et al.  Segment-based injection attacks against collaborative filtering recommender systems , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[19]  HorngShi-Jinn,et al.  A novel intrusion detection system based on hierarchical clustering and support vector machines , 2011 .

[20]  Mo Qian,et al.  Overview of Web Spammer Detection , 2014 .

[21]  Shih-Hsiang Huang,et al.  βPβP: A novel approach to filter out malicious rating profiles from recommender systems , 2013, Decis. Support Syst..

[22]  Fillia Makedon,et al.  Attack detection in time series for recommender systems , 2006, KDD '06.

[23]  Ching-man Au Yeung,et al.  "Popularity Effect" in User-Generated Content: Evidence from Online Product Reviews , 2014, Inf. Syst. Res..

[24]  Yanchun Zhang,et al.  Shilling attack detection utilizing semi-supervised learning method for collaborative recommender system , 2013, World Wide Web.

[25]  Fengjun Li,et al.  Trust-Aware Review Spam Detection , 2015, 2015 IEEE Trustcom/BigDataSE/ISPA.