Michael P. O'Mahony, Neil J. Hurley, Guenole C. M. Silvestre
In the research to date, the performance of recommender systems has been extensively evaluated across various dimensions. Increasingly, the issue of robustness against malicious attack is receiving attention from the research community. In previous work, we have shown that knowledge of certain domain statistics is sufficient to allow successful attacks to be mounted against recommender systems. In this paper, we examine the extent of domain knowledge that is actually required and find that, even when little such knowledge is known, it remains possible to mount successful attacks.
Content Area: 5. Automated Reasoning
Subjects: 3. Automated Reasoning; 1.10 Information Retrieval
Submitted: May 10, 2005