This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Attacks and Remedies in Collaborative Recommendation
May/June 2007 (vol. 22 no. 3)
pp. 56-63
Bamshad Mobasher, DePaul University
Robin Burke, DePaul University
Runa Bhaumik, DePaul University
J.J. Sandvig, DePaul University
Preserving user trust in recommender system depends on the perception of the system as objective, unbiased, and accurate. However, publicly accessible user-adaptive systems such as collaborative recommender systems present a security problem. Attackers, closely resembling ordinary users, might introduce biased profiles to force the system to adapt in a manner advantageous to them. The authors discuss some of the major issues in building secure recommender systems, including some of the most effective attacks and their impact on various recommendation algorithms. Approaches for responding to these attacks range from algorithmic approaches to designing more robust recommenders, to effective methods for detecting and eliminating suspect profiles.
Index Terms:
collaborative recommendation, trust, user-adaptive systems, security
Citation:
Bamshad Mobasher, Robin Burke, Runa Bhaumik, J.J. Sandvig, "Attacks and Remedies in Collaborative Recommendation," IEEE Intelligent Systems, vol. 22, no. 3, pp. 56-63, May-June 2007, doi:10.1109/MIS.2007.45
Usage of this product signifies your acceptance of the Terms of Use.