A collaborative and multi-agent system for e-mail filtering and classification

Abstract

CAFE (collaborative agents for filtering e-mails) is a multi-agent system to collaboratively filter spam and classify legitimate messages in users' mail stream. CAFE associates a proxy agent with each user, and this agent represents a sort of interface between the user's e-mail client and the e-mail server. With the support of other types of agents, the proxy agent makes a classification of new messages into three categories: ham (good messages), spam and spam-presumed. Ham messages can be in their turn divided on the basis of the sender's identity and reputation. The reputation is collaboratively inferred from users' ratings. The filtering process is performed using three kinds of approach: a first approach based on the usage of an hash function, a static approach using DNSBL (DNS-based black lists) databases and a dynamic approach based on a Bayesian filter. We give a mathematical representation of the system, showing that if users collaborate, the fault probability decreases in proportion to the number of active users