High Performance Pattern Matching Algorithm for Network Security

Abstract

Summary Many network security applications rely on pattern matching to extract the threat from network traffic. The increase in network speed and traffic may make existing algorithms to become a performance bottleneck. Therefore, it is very necessary to develop faster and more efficient pattern matching algorithms in order to overcome the troubles on performance. In this paper, we present a new pattern matching algorithm. The improved algorithm and its working process are described in detail. Together with a new concept of reference point, a twodimensional array redesigned based on novel generated rules in the pre-processing phase, endorse the algorithm a better performance and more efficient. The algorithm also passed tests and is validated. Our experimental results, the average performance of English text and network traffic can be improved up to 24% ~ 31% compared to Boyer-Moore algorithm.