IEEE Project Abstract

As the use of recommender systems becomes generalized in society, the interest in varying the orientation of their recommendations increases. There are Shilling attacks strategies that introduce malicious profiles in collaborative filtering recommender systems in order to promote the own products or services, or to discredit those of the competition. Academic research against shilling attacks has been focused in statistical approaches to detect unusual patterns in user ratings. Nowadays there is a growing research area focused on the design of robust machine learning methods to neutralize malicious profiles inserted into the system. This paper proposes an innovative robust method, based on matrix factorization,to neutralize shilling attacks. Our method obtains the reliability value associated to each prediction of a user to an item. Monitoring unusual reliability variations in the items prediction we can avoid promoting shilling predictions to erroneous recommendations. This paper open provides more than thirteen thousand individual experiments involving a wide range of attack strategies, both push and nuke, in order to test the proposed approach. Results show that the proposed method is able to neutralize most of the existing attacks;its performance only decreases in the not relevant situations: when the attack size is not large enough to affect effectively the recommendations provided by the system.