A Traffic Normalization Location Attention Network for cyber attack detection in Industrial Cyber-Physical Systems

IF 4.8 3区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Ad Hoc Networks Pub Date : 2025-07-14 DOI:10.1016/j.adhoc.2025.103965

Minpeng Cheng, Yongyi Chen, Dan Zhang

引用次数: 0

Abstract

Cyber attacks are known as one of the main threats of Industrial Cyber-Physical Systems (ICPSs). Although the existing Deep Learning (DL) -based methods can detect cyber attacks to a certain extent, they have shortcomings in weighting the location information of traffic sampling points and have poor suppression effect on redundant information in the spatial dimension, which may lead to an insufficient performance. Based on the above issues, a Traffic Normalization Location Attention Network (TNLAN) is proposed in this paper. Firstly, the location information between the sampling points is dynamically weighted to improve the network weights of the traffic locations. Then, the scale factors of the batch normalization layer are applied to help the detection network suppress the redundant information in the spatial dimension. The results show that TNLAN outperforms existing methods in detecting cyber attacks.

查看原文本刊更多论文

面向工业信息物理系统网络攻击检测的流量归一化位置关注网络

网络攻击是工业网络物理系统（icps）的主要威胁之一。现有的基于深度学习（Deep Learning， DL）的网络攻击检测方法虽然能在一定程度上检测到网络攻击，但在对流量采样点的位置信息进行加权处理方面存在不足，对空间维度上的冗余信息抑制效果较差，可能导致性能不理想。基于上述问题，本文提出了一种交通归一化位置注意网络（TNLAN）。首先，对采样点之间的位置信息进行动态加权，提高流量位置的网络权重；然后，利用批归一化层的尺度因子帮助检测网络抑制空间维度上的冗余信息。结果表明，TNLAN在检测网络攻击方面优于现有的方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Ad Hoc Networks 工程技术-电信学

CiteScore

10.20

自引率

4.20%

发文量

131

审稿时长

4.8 months

期刊介绍： The Ad Hoc Networks is an international and archival journal providing a publication vehicle for complete coverage of all topics of interest to those involved in ad hoc and sensor networking areas. The Ad Hoc Networks considers original, high quality and unpublished contributions addressing all aspects of ad hoc and sensor networks. Specific areas of interest include, but are not limited to: Mobile and Wireless Ad Hoc Networks Sensor Networks Wireless Local and Personal Area Networks Home Networks Ad Hoc Networks of Autonomous Intelligent Systems Novel Architectures for Ad Hoc and Sensor Networks Self-organizing Network Architectures and Protocols Transport Layer Protocols Routing protocols (unicast, multicast, geocast, etc.) Media Access Control Techniques Error Control Schemes Power-Aware, Low-Power and Energy-Efficient Designs Synchronization and Scheduling Issues Mobility Management Mobility-Tolerant Communication Protocols Location Tracking and Location-based Services Resource and Information Management Security and Fault-Tolerance Issues Hardware and Software Platforms, Systems, and Testbeds Experimental and Prototype Results Quality-of-Service Issues Cross-Layer Interactions Scalability Issues Performance Analysis and Simulation of Protocols.