Uncovering anomalous rating behaviors for rating systems

Abstract Personalization collaborative filtering recommendation plays a key component in online rating systems, which also suffers from profile injection attacks in reality. Although anomalous rating detection for online rating systems has attracted increasing attention in recent years, detection performance of the existing methods has not reached an end. Eliminating the impact of interfering information on anomaly detection is a crucial issue for reducing false alarm rates. Moreover, detecting anomalous ratings for unlabeled and real-world data is always a big challenge. In this paper, we investigate a two-stage detection framework to spot anomalous rating profiles. Firstly, interfering rating profiles are determined by comprehensively analyzing the distributions of user activity, item popularity and special ratings in order to eliminate sparse ratings. Based on the reserved rating profiles, combining target item analysis and non-linear structure clustering is then adopted to further determine the concerned attackers. Extensive experimental comparisons in diverse attacks demonstrate the effectiveness of the proposed method compared with competing benchmarks. Additionally, discovering interesting findings including anomalous ratings and items on two real-world datasets, Amazon and TripAdvisor, is also investigated.

[1]  Gillian Dobbie,et al.  Detection of abnormal profiles on group attacks in recommender systems , 2014, SIGIR.

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

[3]  Sheng Huang,et al.  A Hybrid Decision Approach to Detect Profile Injection Attacks in Collaborative Recommender Systems , 2012, ISMIS.

[4]  David C. Wilson,et al.  Attacking item-based recommender systems with power items , 2014, RecSys '14.

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

[6]  Yung-Yu Chuang,et al.  Multiple Kernel Fuzzy Clustering , 2012, IEEE Transactions on Fuzzy Systems.

[7]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[8]  Huseyin Polat,et al.  Shilling attacks against recommender systems: a comprehensive survey , 2014, Artificial Intelligence Review.

[9]  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.

[10]  Bhaskar Mehta.  Unsupervised Shilling Detection for Collaborative Filtering , 2007, AAAI.

[11]  Fuguo Zhang.  Robust Analysis of Network based Recommendation Algorithms against Shilling Attacks , 2015 .

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

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

[14]  Christos Faloutsos,et al.  Detecting anomalies in dynamic rating data: a robust probabilistic model for rating evolution , 2014, KDD.

[15]  Fuzhi Zhang,et al.  HHT-SVM: An online method for detecting profile injection attacks in collaborative recommender systems , 2014, Knowl. Based Syst..

[16]  Dimitrios I. Fotiadis,et al.  Multiple Kernel Learning Algorithms and Their Use in Biomedical Informatics , 2016 .

[17]  Jong-Seok Lee,et al.  Shilling Attack Detection - A New Approach for a Trustworthy Recommender System , 2012, INFORMS J. Comput..

[18]  David C. Wilson,et al.  Mitigating Power User Attacks on a User-Based Collaborative Recommender System , 2015, FLAIRS.

[19]  Gillian Dobbie,et al.  Shilling Attacks Detection in Recommender Systems Based on Target Item Analysis , 2015, PloS one.

[20]  Ji Feng,et al.  Deep Forest: Towards An Alternative to Deep Neural Networks , 2017, IJCAI.

[21]  MengChu Zhou,et al.  An Incremental-and-Static-Combined Scheme for Matrix-Factorization-Based Collaborative Filtering , 2016, IEEE Transactions on Automation Science and Engineering.

[22]  Baoxu Liu,et al.  Attack Detection by Rough Set Theory in Recommendation System , 2010, 2010 IEEE International Conference on Granular Computing.

[23]  Xiangliang Zhang,et al.  Securing Recommender Systems Against Shilling Attacks Using Social-Based Clustering , 2013, Journal of Computer Science and Technology.

[24]  Chengqi Zhang,et al.  Noisy but non-malicious user detection in social recommender systems , 2012, World Wide Web.

[25]  David C. Wilson,et al.  Evil Twins: Modeling Power Users in Attacks on Recommender Systems , 2014, UMAP.

[26]  Christos Faloutsos,et al.  CatchSync: catching synchronized behavior in large directed graphs , 2014, KDD.

[27]  David C. Wilson,et al.  Assessing Impacts of a Power User Attack on a Matrix Factorization Collaborative Recommender System , 2014, FLAIRS.

[28]  Huseyin Polat,et al.  A Novel Shilling Attack Detection Method , 2014, ITQM.

[29]  Taghi M. Khoshgoftaar,et al.  A Survey of Collaborative Filtering Techniques , 2009, Adv. Artif. Intell..

[30]  Christos Faloutsos,et al.  Robust multivariate autoregression for anomaly detection in dynamic product ratings , 2014, WWW.

[31]  Chong-kwon Kim,et al.  PSD: Practical Sybil detection schemes using stickiness and persistence in online recommender systems , 2014, Inf. Sci..

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

[33]  Zhongmin Cai,et al.  Estimating user behavior toward detecting anomalous ratings in rating systems , 2016, Knowl. Based Syst..

[34]  Johan A. K. Suykens,et al.  Optimized Data Fusion for Kernel k-Means Clustering , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Jie Cao,et al.  A comparative study of shilling attack detectors for recommender systems , 2015, 2015 12th International Conference on Service Systems and Service Management (ICSSSM).

[36]  MengChu Zhou,et al.  Generating Highly Accurate Predictions for Missing QoS Data via Aggregating Nonnegative Latent Factor Models , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[37]  Jure Leskovec,et al.  Inferring Networks of Substitutable and Complementary Products , 2015, KDD.

[38]  Wei Wang,et al.  Recommender system application developments: A survey , 2015, Decis. Support Syst..

[39]  Bin Fang,et al.  A novel item anomaly detection approach against shilling attacks in collaborative recommendation systems using the dynamic time interval segmentation technique , 2015, Inf. Sci..

[40]  MengChu Zhou,et al.  An Inherently Nonnegative Latent Factor Model for High-Dimensional and Sparse Matrices from Industrial Applications , 2018, IEEE Transactions on Industrial Informatics.

[41]  Sanjeev R. Kulkarni,et al.  Detection of shilling attacks in recommender systems via spectral clustering , 2014, 17th International Conference on Information Fusion (FUSION).

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

[43]  Liang Du,et al.  Unsupervised Feature Selection with Adaptive Structure Learning , 2015, KDD.

[44]  J. Bobadilla,et al.  Recommender systems survey , 2013, Knowl. Based Syst..

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

[46]  Yue Lu,et al.  Latent aspect rating analysis on review text data: a rating regression approach , 2010, KDD.

[47]  Fuzhi Zhang,et al.  A Meta-learning-based Approach for Detecting Profile Injection Attacks in Collaborative Recommender Systems , 2012, J. Comput..

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

[49]  Jie Cao,et al.  A survey on shilling attack models and detection techniques for recommender systems , 2014 .

[50]  Zhongmin Cai,et al.  Spotting anomalous ratings for rating systems by analyzing target users and items , 2017, Neurocomputing.

[51]  Hanghang Tong,et al.  Panther: Fast Top-k Similarity Search on Large Networks , 2015, KDD.

[52]  Bhaskar Mehta,et al.  Unsupervised strategies for shilling detection and robust collaborative filtering , 2009, User Modeling and User-Adapted Interaction.

[53]  Sanjeev R. Kulkarni,et al.  Graph-based detection of shilling attacks in recommender systems , 2013, 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP).

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

[55]  Thomas Hofmann,et al.  Lies and propaganda: detecting spam users in collaborative filtering , 2007, IUI '07.

[56]  Yi Yang,et al.  Image Clustering Using Local Discriminant Models and Global Integration , 2010, IEEE Transactions on Image Processing.

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

[58]  Yue Lu,et al.  Latent aspect rating analysis without aspect keyword supervision , 2011, KDD.

[59]  Mehdi Shajari,et al.  Defending recommender systems by influence analysis , 2013, Information Retrieval.

[60]  Zhigang Luo,et al.  Detection of shilling attacks in collaborative filtering recommender systems , 2011, 2011 International Conference of Soft Computing and Pattern Recognition (SoCPaR).

[61]  Zongben Xu,et al.  Re-scale AdaBoost for attack detection in collaborative filtering recommender systems , 2015, Knowl. Based Syst..

[62]  Carlos E. Seminario,et al.  Accuracy and robustness impacts of power user attacks on collaborative recommender systems , 2013, RecSys.