模式匹配是入侵检测的重要技术手段,利用多核平台加速模式匹配是近年学术研究的热点。本文重点阐述了利用网络处理器和GPU等平台研究加速入侵检测中模式匹配的原理和实现方法,比较分析了在多核环境下加速模式匹配的主要思路和技术特点,总结并提出了安全性、自适应性、可扩展性和系统性等开放性问题。
Pattern matching is one of the key procedures in IDS, and making use of multi-core platiorms to acceierate pattern matching has become a hot research topic in recent years. The principles and technologies of pattern matching's implementation on multi-core platforms such as network processor and GPU are introduced, and then a summarization of the current methods is given. Finally, the related open research problems remained are proposed, including the security of methods, adaptivity, scalability and system-level consideration.