Securing Tag-based recommender systems against profile injection attacks: A comparative study

This work addresses challenges related to attacks on social tagging systems, which often comes in a form of malicious annotations or profile injection attacks. In particular, we study various countermeasures against two types of threats for such systems, the Overload and the Piggyback attacks. The studied countermeasures include baseline classifiers such as, Naive Bayes filter and Support Vector Machine, as well as a deep learning-based approach. Our evaluation performed over synthetic spam data, generated from del.icio.us, shows that in most cases, the deep learning-based approach provides the best protection against threats.

[1]  Bamshad Mobasher,et al.  Resource recommendation in social annotation systems: A linear-weighted hybrid approach , 2012, J. Comput. Syst. Sci..

[2]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[3]  Gerard Salton,et al.  Term-Weighting Approaches in Automatic Text Retrieval , 1988, Inf. Process. Manag..

[4]  Susan T. Dumais,et al.  A Bayesian Approach to Filtering Junk E-Mail , 1998, AAAI 1998.

[5]  B. O'neill.  Elementary Differential Geometry , 1966 .

[6]  Georgia Koutrika,et al.  Combating spam in tagging systems , 2007, AIRWeb '07.

[7]  Bamshad Mobasher,et al.  Evaluating the Impact of Attacks in Collaborative Tagging Environments , 2009, 2009 International Conference on Computational Science and Engineering.

[8]  Dimiter Tsvetkov,et al.  Using Support Vector Machine as a Binary Classifier , 2005 .

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Robin Burke,et al.  Exploring the Impact of Profile Injection Attacks in Social Tagging Systems ? , 2008 .

[11]  Georgia Koutrika,et al.  Can social bookmarking improve web search? , 2008, WSDM '08.

[12]  S Kullback,et al.  LETTER TO THE EDITOR: THE KULLBACK-LEIBLER DISTANCE , 1987 .

[13]  Isabella Peters,et al.  Using social bookmarks and tags as alternative indicators of journal content description , 2012, First Monday.

[14]  Georgia Koutrika,et al.  Fighting Spam on Social Web Sites: A Survey of Approaches and Future Challenges , 2007, IEEE Internet Computing.

[15]  Guihai Chen,et al.  Resisting Tag Spam by Leveraging Implicit User Behaviors , 2016, Proc. VLDB Endow..

[16]  Gerard Salton,et al.  A vector space model for automatic indexing , 1975, CACM.

[17]  Richard Hans Robert Hahnloser,et al.  Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[18]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[19]  Ed H. Chi,et al.  Perception and understanding of social annotations in web search , 2013, WWW.

[20]  Mehrdad Jalali,et al.  Spam detection in social bookmarking websites , 2013, 2013 IEEE 4th International Conference on Software Engineering and Service Science.

[21]  Fabio Vitali,et al.  Topical tags vs non-topical tags: Towards a bipartite classification? , 2015, J. Inf. Sci..

[22]  Ronald Rousseau,et al.  Similarity measures in scientometric research: The Jaccard index versus Salton's cosine formula , 1989, Inf. Process. Manag..

[23]  Touradj Ebrahimi,et al.  Spam Fighting in Social Tagging Systems , 2012, SocInfo.

[24]  John Langford,et al.  CAPTCHA: Using Hard AI Problems for Security , 2003, EUROCRYPT.