基于深度神经网络的低时延的入侵检测模型  

Low-latency intrusion detection model based on deep neural network

作　　者：杨洪朝 谢英辉[1] 张占 梁芮 YANG Hongzhao;XIE Yinghui;ZHANG Zhan;LIANG Rui(School of Software,Changsha Social Work College,Changsha 410004,China;School of Electrical and Information Engineering,Changsha University of Science and Technology,Changsha 410114,China)

机构地区：[1]长沙民政职业技术学院软件学院,湖南长沙410004 [2]长沙理工大学电气与信息工程学院,湖南长沙410114

出　　处：《传感器与微系统》2025年第3期84-88,共5页Transducer and Microsystem Technologies

基　　金：湖南省自然科学基金项目资助(2022JJ60103);国家自然科学基金资助项目(7217010719,72171026);中国高校产学研创新基金—新一代信息技术创新项目(2021ITA10023);湖南省科普专题项目(2022ZK4045);湖南省社会科学成果评审委员会项目(XSP24YBC538);长沙市自然科学基金(kq2208240);湖南省教育厅科学研究项目(22C1439,23C1075,23C1076)。

摘　　要：为适应物联网(IoT)节点计算能力不足和易受网络攻击等特点,提出融合生成对抗网络(GAN)和长短期记忆网络(LSTM)的低时延的入侵检测模型(GAN-LLD),使模型更好适应IoT对资源的苛刻需求。GAN-LLD模型采用雾结构,将检测模型部署在雾层,进而满足低检测时延要求。为了获取更高的检测率,GAN-LLD模型引入重构损失,通过将数据样本映射至潜在空间,再计算重构损失。最后,利用数据集NSL-KDD验证GAN-LLD模型的性能。仿真结果表明,相比于多变量异常检测(MAD)-GAN模型,提出的GAN-LLD模型具有高的检测率和低的检测时延。To adapt to characteristics of insufficient computing power of the nodes in Internet of Things(IoT)and vulnerable to Cyber-attacks,a low-latency intrusion detection model fuses a generative adversarial network(GAN)and long short-term memory(LSTM)are proposed to make the detection model better adapts to the demanding demands of IoT on resource.The proposed GAN-LLD model adopts fog structure,and the detecting model is deployed in the fog layer to meet the requirement of low-latency detection.In order to achieve higher detection rate,GAN-LLD model recomputes reconstruction loss,by mapping data samples to the latent space.Finally,the performance of GAN-LLD model is verified by NSL-KDD dataset.Simulation results show that the proposed GAN-LLD model has higher detection rate and lower detection latency than the multivariate anomaly detection(MAD)-GAN model.

关 键 词：物联网 入侵检测模型 生成对抗网络 重构损失 检测时延 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]