Class-incremental open-set radio-frequency fingerprints identification based on prototypes extraction and self-attention transformation

doi:10.23919/JSEE.2025.000180

Abstract

Abstract:

In wireless sensor networks, ensuring communication security via specific emitter identification (SEI) is crucial. However, existing SEI methods are limited to closed-set scenarios and lack the ability to detect unknown devices and perform class-incremental training. This study proposes a class-incremental open-set SEI approach. The open-set SEI model calculates radio-frequency fingerprints (RFFs) prototypes for known signals and employs a self-attention mechanism to enhance their discriminability. Detection thresholds are set through Gaussian fitting for each class. For class-incremental learning, the algorithm freezes the parameters of the previously trained model to initialize the new model. It designs specific losses: the RFFs extraction distribution difference loss and the prototype transformation distribution difference loss, which force the new model to retain old knowledge while learning new knowledge. The training loss enables learning of new class RFFs. Experimental results demonstrate that the open-set SEI model achieves state-of-the-art performance and strong noise robustness. Moreover, the class-incremental learning algorithm effectively enables the model to retain old device RFFs knowledge, acquire new device RFFs knowledge, and detect unknown devices simultaneously.

Key words: wireless sensor network, specific emitter identification, open-set identification, class-incremental learning

Cunxiang XIE, Zhaogen ZHONG, Limin ZHANG. Class-incremental open-set radio-frequency fingerprints identification based on prototypes extraction and self-attention transformation[J]. Journal of Systems Engineering and Electronics, 2026, 37(1): 112-126.

Figures/Tables 13

Fig 1

Fig 2

Fig 3

Fig 4

Fig 5

Fig 6

Fig 7

Fig 8

Fig 9

Fig 10

Fig 11

Fig 12

Fig 13

References 30

1	AL-GARADI S M A, MOHAMED A, AL-ALI A K, et al A survey of machine and deep learning methods for Internet of Things (IoT) security. IEEE Communications Surveys and Tutorials, 2020, 22 (3): 1646- 1685. doi: 10.1109/COMST.2020.2988293
2	LIU S Y, CHI C, ZHANG Y, et al Identification and resolution for industrial internet: architecture and key technology. IEEE Internet Things Journal, 2022, 9 (18): 16780- 16794. doi: 10.1109/JIOT.2022.3160737
3	TANG F X, MAO B M, KATO N, et al Comprehensive survey on machine learning in vehicular network: technology, applications and challenges. IEEE Communications Surveys and Tutorials, 2021, 23 (3): 2027- 2057. doi: 10.1109/COMST.2021.3089688
4	ZHANG N, FANG X J, WANG Y, et al Physical-layer authentication for internet of things via WFRFT-based gaussian tag embedding. IEEE Internet of Things Journal, 2020, 7 (9): 9001- 9010. doi: 10.1109/JIOT.2020.3001597
5	SIDDIQUI Z, GAO J, KHURRAM KHAN M An improved lightweight PUF-PKI digital certificate authentication scheme for the internet of things. IEEE Internet of Things Journal, 2022, 9 (20): 19744- 19756. doi: 10.1109/JIOT.2022.3168726
6	NGUYEN T N, TRAN D, CHIEN T V, et al Security-Reliability trade off analysis for SWIPT-and AF-based IoT networks with friendly jammers. IEEE Internet of Things Journal, 2022, 9 (21): 21662- 21675. doi: 10.1109/JIOT.2022.3182755
7	ZAHIB M U, NISAR M D, SHAH M H Radio frequency fingerprint extraction based on multiscale approximate entropy. Physical Communication, 2022, 55, 101927. doi: 10.1016/j.phycom.2022.101927
8	YANG Y, HU A Q, YU J B A practical radio frequency fingerprinting scheme for mobile phones identification. Physical Communication, 2022, 55, 101876. doi: 10.1016/j.phycom.2022.101876
9	QING G W, WANG H F, ZHANG T P Radio frequency fingerprinting identification for Zigbee via lightweight CNN. Physical Communication, 2021, 44, 101250. doi: 10.1016/j.phycom.2020.101250
10	KIM L S, BAE H B, KIL R M, et al Classification of the trained and untrained emitter types based on class probability output networks. Neurocomputing, 2017, 248, 67- 75. doi: 10.1016/j.neucom.2017.01.094
11	ZHUO F, HUANG Y L, CHEN J Radio frequency fingerprint extraction of radio emitter based on I/Q imbalance. Procedia Computer Science, 2017, 107, 472- 477. doi: 10.1016/j.procs.2017.03.092
12	HAN J, ZHANG T, REN D F, et al Mechanism analysis and feature extraction algorithm of communication emitter fingerprint. AEU-International Journal of Electronics and Communications, 2019, 106, 89- 95.
13	SATIJA U, TRIVEDI N, BISWAL G, RAMKUMAR B Specific emitter identification based on variational mode decomposition and spectral features in single hop and relaying scenarios. IEEE Trans. on Information Forensics and Security, 2019, 14 (3): 581- 591. doi: 10.1109/TIFS.2018.2855665
14	SUI J P, LIU Z, LIU L, et al Online non-cooperative radar emitter classification from evolving and imbalanced pulse streams. IEEE Sensors Journal, 2020, 20 (14): 7721- 7730. doi: 10.1109/JSEN.2020.2981976
15	DING L, WANG S L, WANG F G, et al Specific emitter identification via convolutional neural networks. IEEE Communications Letters, 2018, 22 (12): 2591- 2594. doi: 10.1109/LCOMM.2018.2871465
16	HE B X, WANG F G Cooperative specific emitter identification via multiple distorted receivers. IEEE Trans. on Information Forensics and Security, 2020, 15, 3791- 3806. doi: 10.1109/TIFS.2020.3001721
17	QIAN Y H, QI J, KUAI X Y, et al Specific emitter identification based on multi-level sparse representation in automatic identification system. IEEE Trans. on Information Forensics and Security, 2021, 16, 2872- 2884. doi: 10.1109/TIFS.2021.3068010
18	WANG Y, GUI G, GACANIN H, et al An efficient specific emitter identification method based on complex-valued neural networks and network compression. IEEE Journal on Selected Areas in Communications, 2021, 39 (8): 2305- 2317. doi: 10.1109/JSAC.2021.3087243
19	ZHA X, CHEN H, LI T Y, et al Specific emitter identification based on complex Fourier neural network. IEEE Communications Letters, 2022, 26 (3): 592- 596. doi: 10.1109/LCOMM.2021.3135378
20	FU X, PENG Y, LIU Y C, et al Semi-supervised specific emitter identification method using metric-adversarial training. IEEE Internet of Things Journal, 2023, 10 (12): 10778- 10789. doi: 10.1109/JIOT.2023.3240242
21	LIU C, FU X, WANG Y, et al Overcoming data limitations: a few-shot specific emitter identification method using self-supervised learning and adversarial augmentation. IEEE Trans. on Information Forensics and Security, 2024, 19, 500- 513. doi: 10.1109/TIFS.2023.3324394
22	SCHEIRER W J, ROCHA A R, SAPKOTA A, et al Toward open set recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2013, 35 (7): 1757- 1772. doi: 10.1109/TPAMI.2012.256
23	WU Z F, HUA M Y, ZHANG Y B, et al. An open set specific emitter identification method using deep feature embedded discriminator. Proc. of the IEEE 23rd International Conference on Communication Technology, 2023: 1415−1419.
24	WANG W Y, DOU Z, FU J Z, et al. A diffusion model-based open set identification method for specific emitters. Proc. of the IEEE/CIC International Conference on Communications in China, 2023. DOI: 10.1109/ICCC57788.2023.10233588.
25	HUANG S N, GUO L T, FU X, et al. Open-set specific emitter identification leveraging enhanced metric denoising auto-encoders. IEEE Internet of Things Journal, 2024, 12(4): 3453−3462.
26	GUO L T, LIU C, LIU Y C, et al. Towards open-set specific emitter identification using auxiliary classifier generative adversarial network and openMax. IEEE Trans. on Cognitive Communications and Networking, 2024, 10(6): 2019−2028.
27	BELOUADAH E, POPESCU A, KANELLOS I A comprehensive study of class incremental learning algorithms for visual tasks. Neural Networks, 2021, 135, 38- 54. doi: 10.1016/j.neunet.2020.12.003
28	HUANG R H, PENG X Y, CHAI Z, et al Radio frequency fingerprint extraction and authentication towards open-set in noisy channels. Digital Signal Processing, 2024, 146, 104363. doi: 10.1016/j.dsp.2023.104363
29	WANG X K, HOU W H, ZHANG H Y, et al KDE-OCSVM model using Kullback-Leibler divergence to detect anomalies in medical claims. Expert Systems with Applications, 2022, 200, 117056. doi: 10.1016/j.eswa.2022.117056
30	LU W P, YAN X F Visualizing high-dimensional industrial process based on deep reinforced discriminant features and a stacked supervised t-distributed stochastic neighbor embedding network. Expert Systems with Applications, 2021, 186, 115389. doi: 10.1016/j.eswa.2021.115389

[1]	Yongsheng DUAN, Junning ZHANG, Lei XUE, Ying XU. Embedded RF fingerprint interpretation: multi-channel complex residual networks with adaptive sphere space decision boundaries [J]. Journal of Systems Engineering and Electronics, 2026, 37(1): 137-147.
[2]	Yurui ZHAO, Xiang WANG, Liting SUN, Zhitao HUANG. Specific emitter identification based on frequency and amplitude of the signal kurtosis [J]. Journal of Systems Engineering and Electronics, 2025, 36(2): 333-343.
[3]	Rong FAN, Chengke SI, Yi HAN, Qun WAN. RFFsNet-SEI: a multidimensional balanced-RFFs deep neural network framework for specific emitter identification [J]. Journal of Systems Engineering and Electronics, 2024, 35(3): 558-574.
[4]	Kesong CHEN, Yu ZHANG. A consensus time synchronization protocol in wireless sensor network [J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1465-1472.
[5]	Haipeng LI, Dazheng FENG, Xiaohui WANG. Optimization method of linear barrier coverage deployment for multistatic radar [J]. Journal of Systems Engineering and Electronics, 2023, 34(1): 68-80.
[6]	Xiaoyuan LUO, Wenjing ZHONG, Xiaolei LI, Xinping GUAN. Rigid graph-based three-dimension localization algorithm for wireless sensor networks [J]. Journal of Systems Engineering and Electronics, 2018, 29(5): 927-936.
[7]	Yuxing MAO, Huiyuan ZHAO, Dongmei YAN. Weak node protection to maximize the lifetime of wireless sensor networks [J]. Journal of Systems Engineering and Electronics, 2018, 29(4): 693-706.
[8]	Umer JAVED, Di HE, Peilin LIU, Yueming YANG. Frequency hopping in IEEE 802.15.4 to mitigate IEEE 802.11 interference and fading [J]. Journal of Systems Engineering and Electronics, 2018, 29(3): 445-455.
[9]	Hailin Feng and Jieyu Dong. Reliability analysis for WSN based on a modular k-out-of-n system [J]. Systems Engineering and Electronics, 2017, 28(2): 407-412.
[10]	Xuewen Liu, Song Xiao, and Lei Quan. Optical SDMA for applying compressive sensing in WSN [J]. Systems Engineering and Electronics, 2016, 27(4): 780-.
[11]	Tiebing Wang, Miao Li, Xueying Wang, Wei An, and Yiyu Zhou. C60-based clustering scheme for sensor management in STSS [J]. Journal of Systems Engineering and Electronics, 2015, 26(5): 993-999.
[12]	Guangzhu Chen, Qingchun Meng, and Lei Zhang. Chain-type wireless sensor network node scheduling strategy [J]. Journal of Systems Engineering and Electronics, 2014, 25(2): 203-210.
[13]	Chun Zhang and Shumin Fei. Energy efficient target tracking algorithm using cooperative sensors [J]. Journal of Systems Engineering and Electronics, 2012, 23(5): 640-648.
[14]	Gengzhong Zheng, Sanyang Liu, and Xiaogang Qi. Clustering routing algorithm of wireless sensor networks based on Bayesian game [J]. Journal of Systems Engineering and Electronics, 2012, 23(1): 154-159.
[15]	Liang Xue, Zhixin Liu, and Xinping Guan. Prediction-based protocol for mobile target tracking in wireless sensor networks [J]. Journal of Systems Engineering and Electronics, 2011, 22(2): 347-352.