Effective Attack Models for Shilling Item-Based Collaborative Filtering Systems

This paper proposes a new attack model that focuses on a subset of users with similar tastes and shows that such an attack can be highly successful against an item-based algorithm.

Abstract

Significant vulnerabilities have recently been identified in collaborative filtering recommender systems. These vulnerabilities mostly emanate from the open nature of such systems and their reliance on userspecified judgments for building profiles. Attackers who cannot be readily distinguished from ordinary users may introduce biased data in an attempt to force the system to “adapt ” in a manner advantageous to them. A handful of simple attack models have, so far, been identified, and there appear to be significant differences in the susceptibility of different recommendation techniques to these attacks. In particular, item-based collaborative filtering has been found to offer some security advantages over userbased collaborative filtering. Our research in secure personalization is examining a range of more complex attack models and recommendation techniques, paying particular attention to the costs and benefits of mounting an attack. In this paper, we take a closer look at item-based collaborative filtering. In particular, we propose a new attack model that focuses on a subset of users with similar tastes and show that such an attack can be highly successful against an item-based algorithm.