Self-Addressable Memory-Based FSM: A Scalable Intrusion Detection Engine

摘要

One way to detect and thwart a network attack is to compare each incoming packet with predefined patterns, also called an attack pattern database, and raise an alert upon detecting a match. This article presents a novel pattern-matching engine that exploits a memory-based, programmable state machine to achieve deterministic processing rates that are independent of packet and pattern characteristics. Our engine is a self-addressable memory-based finite state machine (SAMFSM), whose current state coding exhibits all its possible next states. Moreover, it is fully reconfigurable in that new attack patterns can be updated easily. A methodology was developed to program the memory and logic. Specifically, we merge u22non-equivalentu22 states by introducing u22super charactersu22 on their inputs to further enhance memory efficiency without adding labels. SAM-FSM is one of the most storage-efficient machines and reduces the memory requirement by 60 times. Experimental results are presented to demonstrate the validity of SAM-FSM.