基于GRU-FedAdam的工业物联网入侵检测方法
The intrusion detection method for IIoT based on GRU-FedAdam
谢承宗 1王禹贺 1王佰多 1李世明1
作者信息
- 1. 哈尔滨师范大学 计算机科学与信息工程学院, 黑龙江 哈尔滨 150025
- 折叠
摘要
针对工业物联网中的入侵检测存在数据隐私泄露和训练时间长的问题,提出一种基于GRU-FedAdam的入侵检测方法.该方法首先采用联邦学习协作训练入侵检测模型,保护客户端数据隐私;其次,构建基于门控循环单元(GRU)的入侵检测模型并采用Adam优化算法,提高客户端模型的训练速度.选用TON_IoT数据集为实验数据,经过两轮通信轮次计算,训练时间比单层LSTM模型减少4s;利用Adam算法训练模型比SGD算法收敛速度更快,入侵检测模型准确率为0.99.实验结果表明,基于GRU-FedAdam的入侵检测方法在保护数据隐私的情况下,可减少训练时间和获得更好的入侵检测效果.
Abstract
Aiming at the problems of data privacy leakage and long training time of intrusion detection methods in Industrial Inter-net of Things,this paper proposes an intrusion detection method based on GRU-FedAdam.The method firstly adopts federated learning to collaboratively train the intrusion detection model to protect the client data privacy,secondly adopts an intrusion detec-tion model based on the gated recurrent unit(GRU)and Adam optimization algorithm to increase the training speed of the client model.In this paper,the TON_IoT dataset is selected as the experimental data,and the training time is reduced by 4 s compared with the single layer LSTM model after two communication rounds of computation;the training model using Adam algorithm con-verges faster than the SGD algorithm,and the accuracy of the intrusion detection model reaches 0.99.Experimental results show that the intrusion detection method based on GRU-FedAdam can effectively reduce training time and achieve superior intrusion de-tection performance while preserving data privacy.
关键词
工业物联网/入侵检测/GRU/联邦学习Key words
Industrial Internet of Things/intrusion detection/GRU/federated learning引用本文复制引用
基金项目
中国高校产学研创新基金(2022HS055)
河南省高等学校重点科研项目(21A413001)
出版年
2024
国家科技期刊平台
NSTL
万方数据