基于优化支持向量机的网络入侵检测技术研究

Network Intrusion Detection Based on Improved Support Vector Machine

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入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。讨论了支持向量机优化算法及其在入侵检测中的应用。实验表明,基于优化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 must be needed in any integral complete security network system. The serious security problems require better performance for intrusion detection system. The traditional intrusion detection systems have high false negative rate, So it is important to introduce machine learning into intrusion detection systems to improve the performance. Support vector machine （SVM） is one kind of the machine learning technologies based on the statistic learning theory （SLT）. It found its application in intrusion detection successful. Discuss the applications of improved SVM algorithm. The experiment proves that detecting intrusion based on optimized SVM improves the detection performance.