Detecting abnormal profiles in collaborative filtering recommender systems

摘要

Personalization collaborative filtering recommender systems (CFRSs) are the crucial components of popular E-commerce services. In practice, CFRSs are also particularly vulnerable to "shilling" attacks or "profile injection" attacks due to their openness. The attackers can inject well-designed attack profiles into CFRSs in order to bias the recommendation results to their benefits. To reduce this risk, various detection techniques have been proposed to detect such attacks, which use diverse features extracted from user profiles. However, relying on limited features to improve the detection performance is difficult seemingly, since the existing features can not fully characterize the attack profiles and genuine profiles. In this paper, we propose a novel detection method to make recommender systems resistant to such attacks. The existing features can be briefly summarized as two aspects including rating behavior based and item distribution based. We firstly formulate the problem as finding a mapping model between rating behavior and item distribution by exploiting the least-squares approximate solution. Based on the trained model, we design a detector by employing a regressor to detect such attacks. Extensive experiments on both the MovieLens-100K and MovieLens-ml-latest-small datasets examine the effectiveness of the proposed detection method. Experimental results demonstrate the outperformance of the proposed approach in comparison with benchmarked method including KNN.