摘要
为了有效增强网络入侵的检测效果,尽可能地预防网络入侵行为的发生,文中基于协同量子粒子群CQPSO算法以及最小二乘支持向量机LSSVM,建立了CQPSO-LSSVM网络入侵检测模型。该模型利用CQPSO算法对网络入侵的相关特征进行选择,从而获得最优特征子集,减少后续LSSVM所需处理的输入特征给数,有效降低计算量,并提高检测效率。经过KDD CUP 99数据集的仿真测试实验,该模型检测效果良好,具有较高的检测率、较低的误报率和漏报率,且检测速率较快,能够满足网络入侵检测的实时性与准确性的要求,为相关网络入侵检测模型的设计和建立提供参考。
In order to effectively enhance the effect of network intrusion detection and prevent the network intrusion,the CQPSO-LSSVM network intrusion detection model based on the Cooperative Quantum Particle Swarm Optimization（CQPSO）algorithm and Least Square Support Vector Machine（LSSVM）is established in this paper. The model uses CQPSO algorithm to select the relevant features of network intrusion,obtaining the optimal feature subset and reducing the number of input features required for LSSVM processing,which can effectively reduce the amount of calculation and improve the detection efficiency. After the simulation test with KDD CUP 99 data set,it can be found that the model can operate well with high detection rate,low false positive rate and false negative rate as well as rapid detection rate,which can meet the requirements of real-time and accuracy of the network intrusion detection,providing reference for the design and establishment of relevant network intrusion detection models.
作者
李治国
LI Zhi-guo(91550 Unit of PLA, Dalian 116023, China)
出处
《电子设计工程》
2018年第11期81-85,共5页
Electronic Design Engineering
关键词
协同量子粒子群算法
最小二乘支持向量机
网络入侵检测
KDD
CUP
99数据集
Cooperative Quantum Particle Swarm Optimization （CQPSO） algorithm
Least Square Support Vector Machine （LSSVM）
network intrusion detection
KDD CUP 99 data set
