Publicly-accessible adaptive systems such as recommender systems present a security problem. 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. Secure personalization is the study of how such public systems can be made more robust in the face of such attacks. This research was supported in part by the National Science Foundation Cyber Trust program under Grant IIS-0430303.

• Robin Burke
• Bamshad Mobasher
• Runa Bhaumik
• Chad Williams
• JJ Sandvig

On publications and other material are available on the project wiki.

Groups at the University of Minnesota and at University College Dublin are doing research in this area.