基于CNN-CBAM的虚假数据注入攻击辨识研究

周先军; 王茹; 刘航; 金波

doi:10.13756/j.gtxyj.2024.230125

您当前的位置：

首页 >

文章列表页 >

基于CNN-CBAM的虚假数据注入攻击辨识研究

光通信系统与网络技术 | 更新时间：2024-05-30

- 基于CNN-CBAM的虚假数据注入攻击辨识研究
- Research on False Data Injection Attack Identification based on CNN-CBAM
- 光通信研究 2024年第3期页码：23012501-23012507
- 作者机构：
  
  湖北工业大学　电气与电子工程学院，武汉　430068
- 作者简介：
  
  周先军（1970-），男，湖北武汉人。副教授，博士，主要研究方向为无线网络、移动通信和深度学习等。
  王茹，研究生。E-mail：314742910@qq.com
- 基金信息：
  
  国家自然科学基金资助项目(61901165;61601177);湖北省自然科学基金资助项目(2019CFB530)
- DOI：10.13756/j.gtxyj.2024.230125
  中图分类号： TN92
- 纸质出版日期：2024-06-10，
  
  收稿日期：2023-08-06，
  
  修回日期：2023-08-28，
扫描看全文
周先军，王茹，刘航，等.基于CNN-CBAM的虚假数据注入攻击辨识研究[J].光通信研究，2024（3）：230125.

Zhou X J, Wang R, Liu H, et al. Research on False Data Injection Attack Identification based on CNN-CBAM[J]. Study on Optical Communications, 2024（3）：230125.
周先军，王茹，刘航，等.基于CNN-CBAM的虚假数据注入攻击辨识研究[J].光通信研究，2024（3）：230125. DOI： 10.13756/j.gtxyj.2024.230125.

Zhou X J, Wang R, Liu H, et al. Research on False Data Injection Attack Identification based on CNN-CBAM[J]. Study on Optical Communications, 2024（3）：230125. DOI： 10.13756/j.gtxyj.2024.230125.

摘要

【目的】

针对当前智能电网受到网络攻击时，未能及时锁定网络攻击位置实现快速部署防御策略的问题。

【方法】

文章提出了一种融合卷积注意力模块（CBAM）的卷积神经网络（CNN）模型（即CNN-CBAM模型）对虚假数据注入攻击（FDIA）位置进行检测。将FDIA的攻击辨识问题建模为一种多标签分类问题，CNN用于提取数据的空间特征，CBAM直接融合到CNN模块的卷积操作后，不仅能从空间域的角度关注重要的参数信息，同时还考虑了通道域上的特征关系，从两个维度对输入数据进行注意力分配，以提升模型的性能。

【结果】

在电气和电子工程师协会（Institute of Electrical and Electronics Engineers，IEEE）14和IEEE118节点系统上对所提出的CNN-CBAM模型FDIA位置检测的性能进行验证，实验结果表明，CNN-CBAM在IEEE14和IEEE118节点系统上的FDIA位置检测率分别为98.25%和96.72%。

【结论】

与其他方法相比，文章所提出的CNN-CBAM模型能够有效地提取数据间的时空特性，提高FDIA存在性和攻击位置辨识精度，并具有更好的鲁棒性。

Abstract

【Objective】

It is always difficult to timely locate the location of the network attack and achieve rapid deployment of defense strategies when the smart grid is attacked by the network.

【Methods】

In order to solve this problem

this article proposes a Convolutional Neural Network (CNN) model that integrates Convolutional Block Attention Modules (CBAM) (CNN-CBAM) to detect False Data Injection Attack (FDIA) positions. The attack identification problem of FDIA is modeled as a multi label classification problem

where CNN is used to extract spatial features of the data. The CBAM module can be directly integrated into the convolution operation of the CNN module

which not only focuses on important parameter information from the perspective of spatial domain

but also considers feature relationships in the channel domain

and allocates attention to the input data from two dimensions to improve the performance of the model.

【Results】

The performance of the proposed CNN-CBAM network FDIA position detection model is verified on Institute of Electrical and Electronics Engineers (IEEE) 14 and IEEE118 node systems. The experimental results show that the FDIA position detection rates of CNN-CBAM on IEEE14 and IEEE118 node systems are 98.25%and 96.72%

respectively.

【Conclusion】

Compared with other methods

the CNN-CBAM network model proposed in this paper can effectively extract the spatiotemporal characteristics between data

with improved existence of FDIA. It also im-proves the accuracy of attack location identification with better robustness.

关键词

智能电网虚假数据注入攻击卷积注意力模块卷积神经网络

Keywords

smart gridFDIACBAMCNN

references

He Y, Mendis G J, Wei J. Real-time Detection of False Data Injection Attacks in Smart Grid: A Deep Learning-based Intelligent Mechanism[J]. IEEE Transactions on Smart Grid, 2017, 8(5): 2505-2516.

曾俊娆, 李鹏, 高莲, 等. 基于TNPE的智能电网虚假数据注入攻击检测[J]. 中国安全生产科学技术, 2021, 17(3): 124-129.

Zeng J R, Li P, Gao L, et al. Detection of False Data Injection Attacks in Smart Grids based on TNPE[J]. China Security Production Science and Technology, 2021, 17(3): 124-129.

Hu P. Detection of False Data Injection Attacks in Smart Grids based on Expectation Maximization[J]. Sensors, 2023, 23(3): 1683.

刘平英, 李家康, 郑柏超. 信息物理系统的监督滑模安全控制设计[J]. 国外电子测量技术, 2021, 40(12): 159-164.

Liu P Y, Li J K, Zheng B C. Design of Supervised Sliding Mode Security Control for Information Physics Systems[J]. Foreign Electronic Measurement Technology, 2021, 40(12): 159-164.

Bo X. Active Defense Research Against False Data Injection Attacks of Power CPS based on Data-Driven Algorithms[J]. Energies, 2022, 15(19): 7432.

Zhang F, Yang Q. False Data Injection Attack Detection in Dynamic Power Grid: A Recurrent Neural Network-based Method[J]. Frontiers in Energy Research, 2022, 10: 1005660.

Rashedm M, Kamruzzaman J, Gondal , et al. False Data Detection in a Clustered Smart Grid Using Unscented Kalman Filter[J]. IEEE Access, 2022, 10: 78548-78556.

Li Q, Zhang J, Zhao J, et al. Adaptive Hierarchical Cyber Attack Detection and Localization in Active Distribution Systems[J]. IEEE Transactions on Smart Grid, 2022, 13(3): 2369-2380.

Huang X, Qin Z, Xie M, et al. Defense of Massive False Data Injection Attack via Sparse Attack Points Considering Uncertain Topological Changes[J]. Journal of Modern Power Systems and Clean Energy, 2022, 10(6): 1588-1598.

吴迪. 虚假数据攻击下电力系统安全检测技术研究[D]. 秦皇岛: 燕山大学, 2020.

Wu D. Research on Power System Security Detection Technology under False Data Attacks[D]. Qinhuangdao: Yanshan University, 2020.

孙立钧, 顾雪平, 刘彤, 等. 一种基于深度强化学习算法的电网有功安全校正方法[J]. 电力系统保护与控制, 2022, 50(10): 114-122.

Sun L J, Gu X P, Liu T, et al. A Deep Reinforcement Learning Algorithm based Active Power Safety Correction Method for Power Grids[J]. Power System Protection and Control, 2022, 50(10): 114-122.

Ganjkhani M, Gilanifar M, Giraldo J, et al. Integrated Cyber and Physical Anomaly Location and Classification in Power Distribution Systems[J]. IEEE Transactions on Industrial Informatics, 2021, 17(10): 7040-7049.

Wang S, Bi S, Zhang Y J A. Locational Detection of the False Data Injection Attack in a Smart Grid: A Multilabel Classification Approach[J]. IEEE Internet of Things Journal, 2020, 7(9): 8218-8227.

Shen K L, Yan W X, Ni H Y, et al. Localization of False Data Injection Attack in Smart Grids based on SSA-CNN[J]. Information, 2023, 14(3): 180.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于卷积神经网络的SCMA-VLC接收机研究

配电网通信系统稳定运行研究分析

基于CNN的可见光屏幕通信识别与解析机制