基于混沌算法的地震信息网络入侵检测研究

为改善传统的基于机器学习的网络入侵检测方法只能检测已知入侵行为,对于未知入侵行为的检测存在误警率高、时效性差的不足,提出一种基于混沌算法的地震信息网络入侵检测方法。创建候选地震信息网络特征-混沌变量映射模型,实现变量之间的转化;采用混沌变量迭代演化算法进行地震信息网络特征选择;使用支持向量机对最优特征进行学习,为提高地震信息网络入侵检测精度,利用柯西蜂群算法对支持向量机参数进行寻优,建立网络入侵检测优化模型。仿真实验证明,基于混沌算法的地震信息网络入侵检测方法能有效实现高检测率、低误报率的入侵检测,具有很高的应用优势。

Intrusion Detection of the Seismic Information NetworkBased on the Chaos Algorithm

The traditional machine-learning-based network intrusion detection method can only detect the known intrusion behavior and has the disadvantages of high false alarm rate and poor timeliness when detecting unknown intrusion behavior. In this study, a new seismic information network intrusion detection method based on the chaos algorithm is proposed. First, the candidate seismic information network feature-chaos variable mapping model is created to enable the transformation between variables, and the chaos variable iterative evolution algorithm is used to select seismic information network features. Then, the support vector machine is used to learn optimal features. Finally, to improve the detection accuracy of seismic information network intrusion, the Cauchy bee colony algorithm is adopted to optimize the parameters of the support vector machine, and the optimization model of network intrusion detection is established. The simulation experiment results show that the seismic information network intrusion detection method based on the chaos algorithm can effectively implement intrusion detection with high detection rate and low false alarm rate, thus having high application advantage.