Categorizing web sites based on content-temporal locality

摘要

A categorization server is coupled to multiple clients via a network. Each client has a security module that monitors web browsing performed on the client and reports a web site browsing stream to the categorization server. The categorization server identifies a site from the browsing stream of a client that is of a known category. The categorization server uses content-temporal locality to determine whether other sites in the browsing stream belong to the same category as the site having the known category. This determination can be performed by assigning probabilities to other sites in the browsing stream, and by considering probabilities assigned to sites in browsing streams of other clients. The categorization server provides categories of sites to the clients, and the client security modules can implement category-based security policies.