为提高复杂环境下网络入侵检测的准确率和降低误报率,提出了一种基于深度置信网络和支持向量机的网络信息安全检测算法.运用DBN提取大量复杂的网络入侵特征属性数据的主要特征个,之后运用SVM进行网络入侵检测.研究结果表明,与DBN和SVM相比,DBN-SVM进行网络入侵检测具有更高的检测准确率和更低的误报率,为网络入侵检测和预警提供新的方法和途径.%In order to improve the accuracy and reduce the false alarm rate of network intrusion detection in complex environment, a network information security detection algorithm based on depth belief network (DBN) and support vector machine is proposed. DBN is used to extract a large number of complex network intrusion characteristic attribute data, then SVM is used for network intrusion detection. The results show compared with DBN and SVM, DBN-SVM has higher detection accuracy and lower false alarm rate, and provides a new method for network intrusion detection and early warning.
展开▼
