Visual analysis method for RF fingerprint based on important region localization and masking

Liu Wenbin; Fan Pingzhi; Yang Jiahuang; Li Yukai; Wang Yuhao; Meng Hua

doi:10.11884/HPLPB202436.230380

Volume 36 Issue 4

Feb. 2024

Turn off MathJax

Article Contents

Article Navigation > High Power Laser and Particle Beams > 2024 > 36(4): 043019

Liu Wenbin, Fan Pingzhi, Yang Jiahuang, et al. Visual analysis method for RF fingerprint based on important region localization and masking[J]. High Power Laser and Particle Beams, 2024, 36: 043019. doi: 10.11884/HPLPB202436.230380

Citation:

Liu Wenbin, Fan Pingzhi, Yang Jiahuang, et al. Visual analysis method for RF fingerprint based on important region localization and masking[J]. High Power Laser and Particle Beams, 2024, 36: 043019. doi: 10.11884/HPLPB202436.230380

Citation:

PDF( 17466 KB)

Visual analysis method for RF fingerprint based on important region localization and masking

doi: 10.11884/HPLPB202436.230380

Liu Wenbin^{1, 2
,},
Fan Pingzhi¹,
Yang Jiahuang³,
Li Yukai³,
Wang Yuhao³,
Meng Hua^{3
,
,}

1.
School of Information Science & Technology, Southwest Jiaotong University, Chengdu 611756, China
2.
The 30th Research Institute of China Electronics Technology Group Corporation, Chengdu 610041, China
3.
School of Mathematics, Southwest Jiaotong University, Chengdu 611756, China

Received Date: 2023-10-30
Accepted Date: 2024-01-22
Rev Recd Date: 2023-12-19

Available Online: 2024-03-15

Publish Date: 2024-02-29

Abstract

Abstract

A Grad-CAM based visualizing method for important regions is proposed for the interpretability of RF fingerprint extraction and deep learning models of time-domain pulse signal samples. The impact of important regions on RF fingerprint recognition results is analyzed through multiple mask tests of important regions. Based on signal samples of 10 emitters, the test results of two ResNet models with different layers are compared. It is found that the proposed method can distinguish different types of signals and present individual differences. Analysis shows that this method can detect important regional localization differences when different emitters send the same signal, and can visually reflect the spatial distance of RF fingerprint characteristics, as well as the differences in feature representation and fingerprint localization accuracy of different models; At the same time, it is found that masks for important areas are more prone to false predictions, which proves the existence of RF fingerprints related to time-frequency characteristics in specific signals, and can assist in visualizing key points that affect the recognition of RF fingerprint samples.
- interpretability,
- radio frequency fingerprint,
- deep learning,
- visualization,
- signal characteristics

FullText(HTML)

References(15)

References

[1]	Al-Shawabka A, Restuccia F, D’Oro S, et al. Exposing the fingerprint: dissecting the impact of the wireless channel on radio fingerprinting[C]//Proceedings of the IEEE INFOCOM 2020 - IEEE Conference on Computer Communications. 2020: 646-655.
[2]	Liu W B, Fan P Z, Wang M H, et al. Optical, acoustic and electromagnetic vulnerability detection for information security[J]. Journal of Physics:Conference Series, 2021, 1775: 012001. doi: 10.1088/1742-6596/1775/1/012001
[3]	刘文斌, 丁建锋, 寇云峰, 等. 物理隔离网络电磁漏洞研究[J]. 强激光与粒子束, 2019, 31:103215 doi: 10.11884/HPLPB201931.190132 Liu Wenbin, Ding Jianfeng, Kou Yunfeng, et al. Research on electromagnetic vulnerability of air-gapped network[J]. High Power Laser and Particle Beams, 2019, 31: 103215 doi: 10.11884/HPLPB201931.190132
[4]	José A. Gutiérrez del Arroyo Pérez. Learning robust radio frequency fingerprints using deep convolutional neural networks[D]. USA: Air Force Institute of Technology, 2022.
[5]	Yang Zhou, Liu Ninghao, Hu Xiaben, et al. Tutorial on deep learning interpretation: a data perspective[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2022: 5156-5159.
[6]	Srivastava G, Jhaveri R H, Bhattacharya S, et al. XAI for cybersecurity: state of the art, challenges, open issues and future directions[DB/OL]. arXiv preprint arXiv: 2206.03585, 2022.
[7]	李辉. 基于类激活图的卷积神经网络可视化解释方法研究[D]. 长春: 吉林大学, 2023 Li Hui. Research on visual interpretable method of convolutional neural networks based on class activation mapping[D]. Changchun: Jilin University, 2023
[8]	Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. 2017: 618-626.
[9]	Kim J, Oh J, Heo T Y. Acoustic scene classification and visualization of beehive sounds using machine learning algorithms and grad-CAM[J]. Mathematical Problems in Engineering, 2021, 2021: 5594498.
[10]	梁先明, 倪帆, 陈文洁, 等. 基于时频Grad-CAM的调制识别网络可解释研究[J/OL]. 西南交通大学学报, 2022. https://kns.cnki.net/kcms/detail/51.1277.u.20220608.1636.008.html Liang Xianming, Ni Fan, Chen Wenjie, et al. Interpretability of modulation recognition network based on time-frequency grad-CAM[J/OL]. Journal of Southwest Jiaotong University, 2022. https://kns.cnki.net/kcms/detail/51.1277.u.20220608.1636.008.html.
[11]	倪帆. 基于可解释深度学习的通信信号调制识别算法研究[D]. 成都: 西南交通大学, 2022 Ni Fan. Research on communication signal modulation recognition algorithm based on interpretable deep learning[D]. Chengdu: Southwest Jiaotong University, 2022
[12]	刘文斌, 范平志, 李雨锴, 等. 辐射源个体识别的一种可解释性测试架构[J]. 太赫兹科学与电子信息学报, 2023, 21(6): 734-744 Liu Wenbin, Fan Pingzhi, Li Yukai, et al. An interpretable testing architecture for specific emitter identification[J]. Journal of Terahertz Science and Electronic Information Technology, 2023, 21(6): 734-744
[13]	He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016: 770-778.
[14]	Xiao Yao, Wei Xizhang. Specific emitter identification of radar based on one dimensional convolution neural network[J]. Journal of Physics:Conference Series, 2020, 1550: 032114. doi: 10.1088/1742-6596/1550/3/032114
[15]	Wu Bin, Yuan Shibo, Li Peng, et al. Radar emitter signal recognition based on one-dimensional convolutional neural network with attention mechanism[J]. Sensors, 2020, 20: 6350. doi: 10.3390/s20216350