Providing anonymity for on-line social network users

Online social networks such as MySpace and Facebook have become popular platforms for people to make connections, share information, and interact with each other online. In an online social network, user publishing activities such as sending messages and posting photos, represent online interactions between friends. As more and more businesses use social networks as a means to propagate their "brand name" and distribute information about their product, a good understanding of user publishing characteristics is important to provide better security measures for online social networks. In this work, we look at the implications of social networks with respect to commercial use. We introduce an algorithm, used to classify commercial and personal profiles. The algorithm uses "well-known" social network publishing relationships, such as publisher and age distribution and temporal usage patterns. The result is a classifier which can be used for the identification of commercial and personal profiles; which is applied within an application to provide additional security measures for the protection of personal profiles. The application is facilitated by deploying an anonymity service, used to obfuscate a personal profile when publishing to a commercial profile wall. The service uses impersonation and in-line analysis of OSN activity to provide a seamless approach to the user. In addition, the anonymity service may become a focal point for other security measures, such as SPAM, Antivirus, Malware and Data Loss Prevention (DLP) protection. The objective of the service is to allow personal profiles to maintain anonymity with respect to attribution inference, when publishing to commercial On-line Social Network (OSN) profiles.