Understanding Shilling Attacks and Their Detection Traits: A Comprehensive Survey

The internet is the home for huge volumes of useful data that is constantly being created making it difficult for users to find information relevant to them. Recommendation System is a special type of information filtering system adapted by online vendors to provide recommendations to their customers based on their requirements. Collaborative filtering is one of the most widely used recommendation systems; unfortunately, it is prone to shilling/profile injection attacks. Such attacks alter the recommendation process to promote or demote a particular product. Over the years, multiple attack models and detection techniques have been developed to mitigate the problem. This paper aims to be a comprehensive survey of the shilling attack models, detection attributes, and detection algorithms. Additionally, we unravel and classify the intrinsic traits of the injected profiles that are exploited by the detection algorithms, which has not been explored in previous works. We also briefly discuss recent works in the development of robust algorithms that alleviate the impact of shilling attacks, attacks on multi-criteria systems, and intrinsic feedback based collaborative filtering methods.

[1]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[2]  R. Burke,et al.  A Clustering Approach to Unsupervised Attack Detection in Collaborative Recommender Systems , 2022 .

[3]  R. Burke,et al.  Detection of Obfuscated Attacks in Collaborative Recommender Systems 1 , 2006 .

[4]  Fang-Fang Chua,et al.  Utilizing Learners' Negative Ratings in Semantic Content-based Recommender System for e-Learning Forum , 2018, J. Educ. Technol. Soc..

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

[6]  Miriam El Khoury Badran.  Survey on shilling attacks and their detection algorithms in Recommender Systems , 2019 .

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

[8]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[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]  Archana Bhise,et al.  Smart Billing Using Content-Based Recommender Systems Based on Fingerprint , 2020 .

[11]  Miloslava Cerna,et al.  Modified recommender system model for the utilized eLearning platform , 2020, Journal of Computers in Education.

[12]  Parneet Kaur,et al.  Shilling attack models in recommender system , 2016, 2016 International Conference on Inventive Computation Technologies (ICICT).

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

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

[15]  Thomas Hofmann,et al.  A Survey of Attack-Resistant Collaborative Filtering Algorithms , 2008, IEEE Data Eng. Bull..

[16]  Chen Liang,et al.  An insider attack on shilling attack detection for recommendation systems , 2016, 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS).

[17]  Patrick P. K. Chan,et al.  Shilling attack based on item popularity and rated item correlation against collaborative filtering , 2019, Int. J. Mach. Learn. Cybern..

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

[19]  Peng Zhang,et al.  Multiview Ensemble Method for Detecting Shilling Attacks in Collaborative Recommender Systems , 2018, Secur. Commun. Networks.

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

[21]  Amir H. Gandomi,et al.  Resolving data sparsity and cold start problem in collaborative filtering recommender system using Linked Open Data , 2020, Expert Syst. Appl..

[22]  Bamshad Mobasher,et al.  Attacks and Remedies in Collaborative Recommendation , 2007, IEEE Intelligent Systems.

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

[24]  Flora Amato,et al.  SOS: A multimedia recommender System for Online Social networks , 2017, Future Gener. Comput. Syst..

[25]  Robin Burke,et al.  Identifying Attack Models for Secure Recommendation , 2004 .

[26]  Jian Wang,et al.  Detecting Shilling Attacks with Automatic Features from Multiple Views , 2019, Secur. Commun. Networks.

[27]  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.

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

[29]  Ed H. Chi,et al.  Top-K Off-Policy Correction for a REINFORCE Recommender System , 2018, WSDM.

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

[31]  Patrick Olivier,et al.  Recommender system based on pairwise association rules , 2019, Expert Syst. Appl..

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

[33]  Xiao Ma,et al.  EARS: Emotion-aware recommender system based on hybrid information fusion , 2019, Inf. Fusion.

[34]  Fei Zhang,et al.  Detection Of Shilling Attack In Collaborative Filtering Recommender System By Pca And Data Complexity , 2018, 2018 International Conference on Machine Learning and Cybernetics (ICMLC).

[35]  Bamshad Mobasher,et al.  Detecting Profile Injection Attacks in Collaborative Recommender Systems , 2006, The 8th IEEE International Conference on E-Commerce Technology and The 3rd IEEE International Conference on Enterprise Computing, E-Commerce, and E-Services (CEC/EEE'06).

[36]  Manas Gaur,et al.  A Collaborative Filtering Recommender System in Primary Care: Towards a Trusting Patient-Doctor Relationship , 2018, 2018 IEEE International Conference on Healthcare Informatics (ICHI).

[37]  Peng Zhang,et al.  UD-HMM: An unsupervised method for shilling attack detection based on hidden Markov model and hierarchical clustering , 2018, Knowl. Based Syst..

[38]  Tommaso Di Noia,et al.  Knowledge-enhanced Shilling Attacks for Recommendation , 2020, SEBD.

[39]  Chandni Shah,et al.  A State of Art Survey on Shilling Attack in Collaborative Filtering Based Recommendation System , 2016 .

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

[41]  Robin van Meteren.  Using Content-Based Filtering for Recommendation , 2000 .

[42]  Hamid Hassanpour,et al.  User preferences modeling using dirichlet process mixture model for a content-based recommender system , 2019, Knowl. Based Syst..

[43]  Alfredo Cuzzocrea,et al.  Cognitive-Based Hybrid Collaborative Filtering with Rating Scaling on Entropy to Defend Shilling Influence , 2019, ICNCC.

[44]  Donghui Wang,et al.  A content-based recommender system for computer science publications , 2018, Knowl. Based Syst..

[45]  Rasul Enayatifar,et al.  Efficient clustering in collaborative filtering recommender system: Hybrid method based on genetic algorithm and gravitational emulation local search algorithm. , 2019, Genomics.

[46]  David C. Wilson,et al.  Nuking Item-Based Collaborative Recommenders with Power Items and Multiple Targets , 2016, FLAIRS.

[47]  Fuguo Zhang,et al.  A Survey of Shilling Attacks in Collaborative Filtering Recommender Systems , 2009, 2009 International Conference on Computational Intelligence and Software Engineering.

[48]  Hui Xiong,et al.  Sequential Recommender System based on Hierarchical Attention Networks , 2018, IJCAI.

[49]  Mehrbakhsh Nilashi,et al.  A recommender system based on collaborative filtering using ontology and dimensionality reduction techniques , 2018, Expert Syst. Appl..

[50]  GoldbergDavid,et al.  Using collaborative filtering to weave an information tapestry , 1992 .

[51]  Maral Azizi,et al.  A collaborative filtering recommender system for test case prioritization in web applications , 2018, SAC.

[52]  Douglas W. Oard,et al.  Implicit Feedback for Recommender Systems , 1998 .

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

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

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

[56]  Neil J. Hurley,et al.  Robust Collaborative Recommendation , 2011, Recommender Systems Handbook.

[57]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[58]  Ahmet Murat Turk,et al.  Robustness analysis of multi-criteria collaborative filtering algorithms against shilling attacks , 2019, Expert Syst. Appl..

[59]  Qingshan Li,et al.  Shilling attacks against collaborative recommender systems: a review , 2018, Artificial Intelligence Review.

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

[61]  Tommaso Di Noia,et al.  SAShA: Semantic-Aware Shilling Attacks on Recommender Systems Exploiting Knowledge Graphs , 2020, ESWC.

[62]  Neil J. Hurley,et al.  Recommender Systems: Attack Types and Strategies , 2005, AAAI.

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

[64]  Hesham A. Hefny,et al.  Shilling Attacks Detection in Collaborative Recommender System: Challenges and Promise , 2020, AINA Workshops.

[65]  Panagiotis Adamopoulos,et al.  On Unexpectedness in Recommender Systems , 2013, ACM Trans. Intell. Syst. Technol..

[66]  Ahmet Murat Turk,et al.  A Robust Multi-Criteria Collaborative Filtering Algorithm , 2018, 2018 Innovations in Intelligent Systems and Applications (INISTA).

[67]  Sivaramakrishnan Natarajan,et al.  Enhancing recommendation stability of collaborative filtering recommender system through bio-inspired clustering ensemble method , 2018, Neural Computing and Applications.

[68]  Fernando Ortega,et al.  Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems , 2019, IEEE Access.

[69]  Zunayeed Bin Zahir,et al.  Content-Based Health Recommender System for ICU Patient , 2019, MIWAI.

[70]  Xinxin Niu,et al.  Defending shilling attacks in recommender systems using soft co-clustering , 2017, IET Inf. Secur..