论文部分内容阅读
入侵检测系统是任何一个完整的网络安全系统中必不可缺的部分。日益严峻的安全问题对于检测方法提出更高的要求。传统的入侵检测方法存在误报漏报及实时性差等缺点,将机器学习的技术引人到入侵监测系统之中以有效地提高系统性能具有十分重要的现实意义。支持向量机(SVM)是一种建立在统计学习理论(SLT)基础之上的机器学习方法。被成功地应用到入侵检测领域中。本文讨论了模糊支持向量机优化算法及其在入侵检测中的应用。实验表明,基于模糊支持向量机检测入侵的方法能较大地提高入侵检测系统的性能。
Intrusion detection system is an indispensable part of any complete network security system. Increasingly stringent safety requirements for testing methods put forward higher requirements. The traditional intrusion detection methods have the defects of false positives and false negatives, and introduce the techniques of machine learning into the intrusion detection system to effectively improve the system performance, which is of great practical significance. Support Vector Machine (SVM) is a machine learning method based on Statistical Learning Theory (SLT). Has been successfully applied to the field of intrusion detection. This article discusses the fuzzy support vector machine optimization algorithm and its application in intrusion detection. Experiments show that the method based on fuzzy support vector machine to detect intrusion can greatly improve the performance of intrusion detection system.