新型GAN的WSN异常检测方法  

WSN anomaly detection method based on new GAN

作　　者：刘拥民[1,2] 张钱垒 杨钰津 罗皓懿 黄浩 LIU Yong-min;ZHANG Qian-lei;YANG Yu-jin;LUO Hao-yi;HUANG Hao(School of Computer and Information Engineering,Central South University of Forestry and Technology,Changsha 410004,China;Smart Forest Cloud Research Center,Central South University of Forestry and Technology,Changsha 410004,China)

机构地区：[1]中南林业科技大学计算机与信息工程学院,湖南长沙410004 [2]中南林业科技大学智慧林业云研究中心,湖南长沙410004

出　　处：《计算机工程与设计》2023年第12期3554-3562,共9页Computer Engineering and Design

基　　金：国家自然科学基金项目(31870532);湖南省自然科学基金项目(2021JJ31163);湖南省教育科学“十三五”规划基金项目(XJK20BGD048)。

摘　　要：为实时预警无线传感器网络(WSN)进行数据传输过程中的一系列威胁,提出一种新型生成对抗网络(GAN)的WSN异常检测方法。采用梯度归一化和代价距离改进的GAN目标函数,与改进的对抗学习异常检测方法相结合,能准确、全面地将数据流特征的分布情况映射到潜在空间,使生成器在训练过程中增加生成数据的多样性,提升模型的鲁棒性;引入带有丢失操作的全连接层网络体系,显著增强对WSN中数据流异常状态的识别能力。仿真结果表明,该方法可全面有效地提高入侵检测方法的综合检测效果。To warn a series of threats in the data transmission process of wireless sensor network(WSN)in real time,a new anomaly detection method for generating countermeasure network(GAN)was proposed.The improved GAN objective function with gradient normalization and cost distance was combined with the improved anti learning anomaly detection method,which accurately and comprehensively mapped the distribution of data flow characteristics to the potential space,making the generator increase the diversity of generated data in the training process and improve the robustness of the model.The full connection layer network system with loss operation was introduced,which significantly enhanced the ability to identify the abnormal state of data flow in WSN.The simulation results show that the method can comprehensively and effectively improve the comprehensive detection effect of intrusion detection methods.

关 键 词：无线传感器网络 生成对抗网络 异常检测 梯度归一化 代价距离 目标函数 全连接层网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]