基于软计算集成的入侵检测技术

Intrusion Detection System Based on Ensemble of Soft Computing Techniques

软计算技术越来越广泛地应用于解决各领域的实际问题。文章将多种不同软计算技术的集成应用于入侵检测。由于网络攻击事件的日益增多,建立有效的入侵检测系统对保护信息安全是非常必要的,但要实现这一点仍面临巨大的挑战。分析了两种类型的软计算技术:人工神经网络和支持向量机。实验证明这两种方法的集成在入侵检测的检测精度方面要优于单一方法。

Soft computing techniques are more and more widely used to solve a variety of practical problems. This paper applied the ensemble of different soft computing techniques in intrusion detection system（IDS）. Due to the increasing incidents of network attacks, building effective intrusion detection system is necessary, but it faces great challenges. Two sorts of soft computing techniques are studied：Artificial Neural Networks（ANNs） and Support Vector Machines（SVMs）. Experimental results show that ensemble of ANN and SVM is superior to individual approaches for intrusion detection in terms of classification accuracy.