摘要
随着网络攻击日益复杂和隐蔽,工业互联网入侵检测系统需不断提升识别准确性以保障稳定运行。对此,本文提出一种基于生成对抗网络的入侵检测方法。通过构建三度条件生成对抗网络算法,建立数据空间并融入处理器与分类器,优化模型损失组合计算。基于UNSW_NB15数据集开展分类与对比实验,结果表明,所提方法的准确率、召回率和F1分数分别达到81.91%、82.09%和82.20%,能够有效识别多样化网络流量,满足工业互联网安全需求。
As cyber attacks become increasingly complex and concealed,industrial Internet intrusion detection systems must continuously improve identification accuracy to ensure stable operation.To address this issue,this paper proposes an intrusion detection method based on generative adversarial networks(GANs).A triple conditional GAN algorithm is constructed to establish a data space by incorporating a processor and a classifier,thereby optimizing the combined computation of model losses.Classification and comparative experiments are conducted using the UNSW_NB15 dataset.Results demonstrate that the proposed method achieves accuracy,recall,and F1 scores of 81.91%,82.09%,and 82.20%,respectively,enabling effective identification of diverse network traffic and meeting the security requirements of the industrial Internet.
作者
王阳
谭振江
WANG Yang;TAN Zhenjiang(School of Mathematics and Computer Science,Jilin Normal University,Siping,China,136000)
出处
《福建电脑》
2025年第12期1-8,共8页
Journal of Fujian Computer
关键词
生成对抗网络
入侵检测
工业互联网
深度学习
Generative Adversarial Networks
Intrusion Detection
Industrial Internet
Deep Learning
