PROJECT TITLE :
Supervised approach for detecting average over popular items attack in collaborative recommender systems
Recent research has shown the numerous vulnerabilities of collaborative recommender systems in the face of profile injection attacks, in which malicious users insert faux profiles into the rating database in order to bias the system's output. To cut back this risk, a variety of approaches have been proposed to detect such attacks. Though the present detection approaches will detect the quality kind of these attacks effectively, they perform badly when detecting the recently proposed obfuscated kind of these attacks, for instance, average over fashionable things (AoP) attack. With this downside in mind, during this study the author propose a supervised approach to detect such attack. 1st, he uses the idea of term frequency inverse document frequency (TFIDF) to extract the options of AoP attack. Second, he uses the training set to train support vector machine (SVM) to come up with a SVM-based classifier. Finally, he uses the generated classifier to detect the AoP attack. The experimental results on MovieLens dataset show that the proposed approach will detect AoP attack with high recall and precision.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here