摘要
为了确保网络的安全性,提升异常入侵检测效果,提出小时间尺度网络流量异常入侵检测算法。通过改进的整体经验模态——去趋势波动分析法估计自相似指数,在大时间尺度上,利用自相似指数判断网络流量是否出现异常入侵;若存在异常入侵,则在小时间尺度上依据李氏指数和信号奇异性的相应关系,结合小波变换计算异常网络流量的李氏指数,根据李氏指数的变化情况检测网络流量异常入侵点,确定异常入侵发生时间。实验结果表明:该算法可精准判断小时间段网络流量是否存在异常入侵情况,同时可精准检测异常入侵发生时间;在不同网络流量异常入侵高度时,该算法具备较高的检测精度。
In order to ensure the security of the network and improve the effect of abnonnal intrusion detection,the network traffic abnormal intrusion detection algorithm in small time scale is proposed.The self-similarity index is estimated by the improved overall empirical modal-detrended fluctuation analysis method,and the selP similarity index is used to determine whether abnormal intrusion occurs in network traffic on a large time scale.If there is abnormal intrusion,the Lee's index of abnormal network traffic is calculated on a small time scale according to the corresponding relationship between Lee's index and signal singularity,combined with wavelet transformation.According to the change of Lee's index,the abnormal intrusion point of network traffic is detected and the occurrence time of abnormal intrusion is determined.The experimental results show that the algorithm can accurately determine whether there is abnormal intrusion in the network traffic in a short period of time,and can accurately detect the occurrence time of abnormal intrusion;The algorithm has high detection accuracy at abnormal intrusion heights of different network traffic.
作者
李杰
LI Jie(jiujiang Vocational University,Jiujiang 332000,China)
出处
《内蒙古民族大学学报（自然科学版）》
2023年第1期27-31,共5页
Journal of Inner Mongolia Minzu University：Natural Sciences
基金
江西省教育厅科技项目(GJJ191269)。
关键词
小时间尺度
网络流量
异常入侵
检测算法
自相似指数
李氏指数
Small time scale
Network traffic
Anomaly intrusion
Detection algorithm
Self-similarity index
Lee5s index
