基于人工神经网络的通信网络异常流量攻击识别方法

Identification Method of Abnormal Traffic Attack in Communication Network Based on Artificial Neural Network

由于现行方法在通信网络异常流量攻击识别中应用效果不理想,文中提出了一种基于人工神经网络的通信网络异常流量攻击识别方法。利用采集器从通信网络日志中提取网络流量特征,对网络特征数据进行补偿并过滤重复数据,通过对特征数据的二值化处理,将数据值统一映射到数据区间[0,1],利用滑动窗口函数将特征数据切片处理为多模态数据,并通过人工神经网络对网络异常流量进行分类,以识别网络异常流量攻击,实现基于人工神经网络的通信网络异常流量攻击识别。实验证明,文中提出的方法识别率在95%以上,漏识率在1%以内,能实现对通信网络异常流量攻击的精准识别。

Due to the unsatisfactory application effect of current methods in identifying abnormal traffic attacks in communication networks,this paper proposes an artificial neural network-based method for identifying abnormal traffic attacks in communication networks.Using a collector to extract network traffic features from communication network logs,compensating and filtering duplicate data for network feature data,and mapping data values to data intervals[0,1]through binary processing of feature data.Using a sliding window function to slice feature data into multimodal data,and using an artificial neural network to classify network abnormal traffic and identify network abnormal traffic attacks,achieving identification of communication network abnormal traffic attacks based on artificial neural networks.Experimental results have shown that the proposed method has a recognition rate of over 95%and a miss rate of less than 1%,and can accurately identify abnormal traffic attacks in communication networks.