无线网络终端设备安全脆弱点识别仿真
|
摘要
对无线网络的终端设备安全的脆弱点进行识别,能有效提高网络异常检测的准确率,提升无线网络运行的安全性能,延长网络运行的周期。利用当前方法对无线网络终端脆弱点进行识别时,终端数据比较杂乱,对安全脆弱点进行识别时,存在识别的准确率较差的问题。提出基于混沌RBF神经网络的网络终端安全脆弱点检测的方法。对网络终端信号构建信号模型,对网络终端信号进行抗干扰的滤波进行处理,利用混沌RBF神经网络对网络终端脆弱点进行检测与识别,对混沌时间的序列进行空间的重构得出空间的向量,作为RBF神经网络数据的输入,经过RBF神经网络对网络终端数据拟合函数进行构建,在拟合函数上进行预测,将预测值和真实值存在的偏差进行对比,由此判断检测的信号是否为异常信号,完成对无线网络终端设备安全脆弱点的识别。实验的结果可表明,利用所提方法,能有效对安全脆弱点进行识别,提高了安全脆弱点识别的准确率。
A method to detect security vulnerabilities of network terminal based on chaotic RBF neural network is presented.Firstly,this method built the model for network terminal signal,and the anti-interference filtration was carried out for network terminal signal.Then,chaotic RBF neural network was used to detect and recognize network terminal vulnerabilities.The space reconstruction was carried out for chaotic time series to get space vectors,which were taken as the input of RBF neural network.Through RBF neural network,fitting function of network terminal data was constructed.By comparing the deviation of predicted value and real value,we determined whether the detected signal was an abnormal signal.Thus,we completed the recognition of security vulnerabilities in wireless network terminal equipment.From simulation result,the proposed method can be used to identify vulnerabilities,which improves the accuracy of vulnerability identification.
A method to detect security vulnerabilities of network terminal based on chaotic RBF neural network is presented.Firstly,this method built the model for network terminal signal,and the anti-interference filtration was carried out for network terminal signal.Then,chaotic RBF neural network was used to detect and recognize network terminal vulnerabilities.The space reconstruction was carried out for chaotic time series to get space vectors,which were taken as the input of RBF neural network.Through RBF neural network,fitting function of network terminal data was constructed.By comparing the deviation of predicted value and real value,we determined whether the detected signal was an abnormal signal.Thus,we completed the recognition of security vulnerabilities in wireless network terminal equipment.From simulation result,the proposed method can be used to identify vulnerabilities,which improves the accuracy of vulnerability identification.
引文
[1]袁福祥,等.基于历史数据的异常域名检测算法[J].通信学报,2016,37(10):172-180.
[2]赵建龙,曲桦,赵季红.基于k-近邻域中心偏移的鲁棒性异常检测算法[J].北京邮电大学学报,2017,40(4):0-0.
[3]李宇翀,等.基于多元增量分析的全网络在线异常检测方法[J].上海交通大学学报,2016,50(9):1368-1375.
[4]万叶晶,叶继华,江爱文.一种基于时空相关性和异常检测的改进WSN节能策略[J].传感技术学报,2017,30(8):1267-1273.
[5]王用鑫.煤矿设备中的基于动态模糊与BP神经网络的故障诊断.[J].科技通报,2016,10(32):195-198.
[6]费欢,等.基于多模态数据流的无线传感器网络异常检测方法[J].计算机学报,2017,40(8):1829-1842.
[7]程艳云,张守超,杨杨.基于大数据的时间序列异常点检测研究[J].计算机技术与发展,2016,26(5):139-144.
[8]李兴国,王俊峰.无线网络数据流量异常优化检测仿真研究[J].计算机仿真,2017,34(9):386-389.
[9]蔡美,刘波.基于蚁群算法的异常数据检测方法[J].计算机工程,2016,42(8):166-169.
[10]米捷,王佳欣.多层次数据中心网络流量异常检测算法[J].河南工程学院学报(自然科学版),2017,29(1):62-66.
[2]赵建龙,曲桦,赵季红.基于k-近邻域中心偏移的鲁棒性异常检测算法[J].北京邮电大学学报,2017,40(4):0-0.
[3]李宇翀,等.基于多元增量分析的全网络在线异常检测方法[J].上海交通大学学报,2016,50(9):1368-1375.
[4]万叶晶,叶继华,江爱文.一种基于时空相关性和异常检测的改进WSN节能策略[J].传感技术学报,2017,30(8):1267-1273.
[5]王用鑫.煤矿设备中的基于动态模糊与BP神经网络的故障诊断.[J].科技通报,2016,10(32):195-198.
[6]费欢,等.基于多模态数据流的无线传感器网络异常检测方法[J].计算机学报,2017,40(8):1829-1842.
[7]程艳云,张守超,杨杨.基于大数据的时间序列异常点检测研究[J].计算机技术与发展,2016,26(5):139-144.
[8]李兴国,王俊峰.无线网络数据流量异常优化检测仿真研究[J].计算机仿真,2017,34(9):386-389.
[9]蔡美,刘波.基于蚁群算法的异常数据检测方法[J].计算机工程,2016,42(8):166-169.
[10]米捷,王佳欣.多层次数据中心网络流量异常检测算法[J].河南工程学院学报(自然科学版),2017,29(1):62-66.