Modern Elektronik Harpte Özgün Yayıcı Tanımlama İçin Derin Öğrenme: Statik Modellerden Bilişsel Adaptasyona

Öz

Modern savaş alanının elektromanyetik spektrumundaki karmaşıklık, Bilişsel Elektronik Harp (EH) sistemleri için düşman unsurlarının sadece tip bazında değil, donanım kusurlarından kaynaklanan Radyo Frekansı Parmak İzleri (RFF) kullanılarak bireysel kimlik bazında tanınmasını (Özgün Yayıcı Tanımlama - SEI) kritik hale getirmiştir. Bu çalışma, SEI literatürünün manuel öznitelik çıkarımından veri güdümlü Derin Öğrenme (DL) yaklaşımlarına olan evrimini; veri ön işleme, mimari tasarımı ve dinamik ortam adaptasyonu perspektifinden kapsamlı bir şekilde incelemektedir. Yapılan analizler, ResNet ve TCN gibi statik derin mimarilerin kontrollü laboratuvar ortamlarında %96'yı aşan başarımlar sergilemesine rağmen; veri kıtlığı (few-shot), bilinmeyen tehditlerin varlığı (open-set) ve karşıt saldırılar (adversarial attacks) gibi gerçek saha koşullarında güvenilirliklerinin %50 seviyelerine kadar düştüğünü göstermektedir. Bu bağlamda çalışma, güvenilirlik açığını kapatmak için Varyasyonel Mod Ayrıştırma (VMD) ve Bispektrum analizi gibi çok modlu (multimodal) özellik füzyonu tekniklerinin önemini vurgulamakta; ayrıca sistemin bilinmeyen tehditleri tanıması ve kendini otonom olarak güncellemesi için Ekstrem Değer Teorisi (EVT) tabanlı açık küme tanıma ve meta-öğrenme stratejilerinin entegrasyonunu önermektedir. Sonuç olarak, elektronik harp üstünlüğünün sürdürülebilirliği için statik modellerden, kendini onaran ve adapte olan bilişsel mimarilere geçişin zorunlu olduğu ortaya konulmuştur.

Anahtar Kelimeler

• Özgün Yayıcı Tanımlama (SEI)
• Bilişsel Elektronik Harp
• Derin Öğrenme
• Radyo Frekansı Parmak İzi (RFF)
• Açık Küme Tanıma
• Az Örnekli Öğrenme

Deep Learning for Specific Emitter Identification in Modern Electronic Warfare: From Static Models to Cognitive Adaptation

Öz

The complexity of the electromagnetic spectrum in the modern battlefield has made it critical for Cognitive Electronic Warfare (EW) systems to identify hostile elements not only by type but also at the individual identity level using Radio Frequency Fingerprints (RFF) originating from hardware imperfections, a process known as Specific Emitter Identification (SEI). This study comprehensively examines the evolution of SEI literature from manual feature extraction to data-driven Deep Learning (DL) approaches from the perspectives of data preprocessing, architectural design, and dynamic environmental adaptation. The analyses demonstrate that although static deep architectures such as Deep Residual Networks (ResNet) and Temporal Convolutional Networks (TCN) exhibit accuracies exceeding 96% in controlled laboratory environments, their reliability drops to levels around 50% under real-world field conditions such as data scarcity (few-shot), the presence of unknown threats (open-set), and adversarial attacks. In this context, the study emphasizes the importance of multimodal feature fusion techniques, such as Variational Mode Decomposition (VMD) and Bispectrum analysis, to bridge the reliability gap; furthermore, it proposes the integration of Extreme Value Theory (EVT)-based open-set recognition and meta-learning strategies for the system to identify unknown threats and update itself autonomously. Consequently, it is revealed that a transition from static models to self-healing and adaptive cognitive architecture is imperative for the sustainability of EW superiority.

Anahtar Kelimeler

• Specific Emitter Identification (SEI)
• Cognitive Electronic Warfare
• Deep Learning
• Radio Frequency Fingerprinting (RFF)
• Open-Set Recognition
• Few-Shot Learning

Kaynakça

1. [1] K. Z. Haigh and J. Andrusenko, Cognitive Electronic Warfare: an artificial intelligence approach. Boston: Artech House, 2021.
2. [2] N. O’Donoughue, Emitter Detection and Geolocation for Electronic Warfare. Artech House, 2019. doi: 10.7249/CB909.
3. [3] H. Peng, K. Xie, and W. Zou, “Research on an Enhanced Multimodal Network for Specific Emitter Identification,” Electronics, vol. 13, no. 3, p. 651, Feb. 2024, doi: 10.3390/electronics13030651.
4. [4] H. Xiao, H. Liu, Y. Zhou, L. Yang, and Z. Ma, “Distributed Unknown Specific Emitter Identification Based on Federated Learning,” in 2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring), Singapore, Singapore: IEEE, Jun. 2024, pp. 1–5. doi: 10.1109/VTC2024-Spring62846.2024.10683366.
5. [5] J. H. Tyler, M. K. M. Fadul, and D. R. Reising, “Considerations, Advances, and Challenges Associated with the Use of Specific Emitter Identification in the Security of Internet of Things Deployments: A Survey,” Information, vol. 14, no. 9, p. 479, Aug. 2023, doi: 10.3390/info14090479.
6. [6] B. He, F. Wang, Y. Liu, and S. Wang, “Specific Emitter Identification Via Multiple Distorted Receivers,” in 2019 IEEE International Conference on Communications Workshops (ICC Workshops), Shanghai, China: IEEE, May 2019, pp. 1–6. doi: 10.1109/ICCW.2019.8757066.
7. [7] L.-Z. Qu, H. Liu, K.-J. Huang, and J.-A. Yang, “Specific Emitter Identification Based on Multi-Domain Feature Fusion and Integrated Learning,” Symmetry, vol. 13, no. 8, p. 1481, Aug. 2021, doi: 10.3390/sym13081481.
8. [8] Z. Wu, M. Du, D. Bi, and J. Pan, “IRelNet: An Improved Relation Network for Few-Shot Radar Emitter Identification,” Drones, vol. 7, no. 5, p. 312, May 2023, doi: 10.3390/drones7050312.

9. [9] S. Cao, Y. Liu, L. Sun, and Y. Lin, “Specific Emitter Identification Based on Knowledge Embedding,” in ICC 2024 - IEEE International Conference on Communications, Denver, CO, USA: IEEE, Jun. 2024, pp. 1661–1666. doi: 10.1109/ICC51166.2024.10622500.
10. [10] G. Gok, Y. K. Alp, and O. Arikan, “A New Method for Specific Emitter Identification With Results on Real Radar Measurements,” IEEE Trans. Inf. Forensics Secur., vol. 15, pp. 3335–3346, 2020, doi: 10.1109/TIFS.2020.2988558.
11. [11] C. Wang, Y. Wang, Y. Zhang, H. Xu, and Z. Zhang, “Open-Set Specific Emitter Identification Based on Prototypical Networks and Extreme Value Theory,” Appl. Sci., vol. 13, no. 6, p. 3878, Mar. 2023, doi: 10.3390/app13063878.
12. [12] Z. Wu, M. Hua, Y. Zhang, S. Wang, P. Liu, and G. Gui, “An Open Set Specific Emitter Identification Method Using Deep Feature Embedded Discriminator,” in 2023 IEEE 23rd International Conference on Communication Technology (ICCT), Wuxi, China: IEEE, Oct. 2023, pp. 1415–1419. doi: 10.1109/ICCT59356.2023.10419658.
13. [13] P. Gupta, P. Jain, and O. G. Kakde, “Deep Learning Techniques in Radar Emitter Identification,” Def. Sci. J., vol. 73, no. 5, pp. 551–563, Aug. 2023, doi: 10.14429/dsj.73.18319.
14. [14] L. Ding, S. Wang, F. Wang, and W. Zhang, “Specific Emitter Identification via Convolutional Neural Networks,” IEEE Commun. Lett., vol. 22, no. 12, pp. 2591–2594, Dec. 2018, doi: 10.1109/LCOMM.2018.2871465.
15. [15] Y. Pan, S. Yang, H. Peng, T. Li, and W. Wang, “Specific Emitter Identification Based on Deep Residual Networks,” IEEE Access, vol. 7, pp. 54425–54434, 2019, doi: 10.1109/ACCESS.2019.2913759.
16. [16] C. Wang et al., “Few-Shot Specific Emitter Identification via Hybrid Data Augmentation and Deep Metric Learning,” Dec. 01, 2022, arXiv: arXiv:2212.00252. doi: 10.48550/arXiv.2212.00252.
17. [17] S. Mu, Y. Zu, S. Chen, S. Yang, Z. Feng, and J. Zhang, “Few-Shot Metric Learning with Time-Frequency Fusion for Specific Emitter Identification,” Remote Sens., vol. 16, no. 24, p. 4635, Dec. 2024, doi: 10.3390/rs16244635.
18. [18] L. Sun, D. Ke, X. Wang, Z. Huang, and K. Huang, “Robustness of Deep Learning-Based Specific Emitter Identification under Adversarial Attacks,” Remote Sens., vol. 14, no. 19, p. 4996, Oct. 2022, doi: 10.3390/rs14194996.
19. [19] D. R. Reising, J. H. Tyler, M. K. M. Fadul, M. R. Hilling, and T. D. Loveless, “Improved RF Fingerprint-based Identity Verification in the Presence of an SEI Mimicking Adversary,” J. Cyber Secur. Mobil., pp. 887–916, Sep. 2024, doi: 10.13052/jcsm2245-1439.1354.
20. [20] U. Satija, N. Trivedi, G. Biswal, and B. Ramkumar, “Specific Emitter Identification Based on Variational Mode Decomposition and Spectral Features in Single Hop and Relaying Scenarios,” IEEE Trans. Inf. Forensics Secur., vol. 14, no. 3, pp. 581–591, Mar. 2019, doi: 10.1109/TIFS.2018.2855665.
21. [21] A. Madhu, P. Prajeesha, and A. S. Kulkarni, “Radar Emitter Identification using Signal Noise and Power Spectrum Analysis in Deep Learning,” in 2022 Fifth International Conference of Women in Data Science at Prince Sultan University (WiDS PSU), Riyadh, Saudi Arabia: IEEE, Mar. 2022, pp. 52–57. doi: 10.1109/WiDS-PSU54548.2022.00022.
22. [22] C. Xie, L. Zhang, and Z. Zhong, “Virtual Adversarial Training‐Based Semisupervised Specific Emitter Identification,” Wirel. Commun. Mob. Comput., vol. 2022, no. 1, p. 6309958, Jan. 2022, doi: 10.1155/2022/6309958.
23. [23] K. Tan, W. Yan, L. Zhang, Q. Ling, and C. Xu, “Semi-Supervised Specific Emitter Identification Based on Bispectrum Feature Extraction CGAN in Multiple Communication Scenarios,” IEEE Trans. Aerosp. Electron. Syst., vol. 59, no. 1, pp. 292–310, Feb. 2023, doi: 10.1109/TAES.2022.3184619.
24. [24] G.-J. Qi and J. Luo, “Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 4, pp. 2168–2187, Apr. 2022, doi: 10.1109/TPAMI.2020.3031898.
25. [25] M. Li, J. Xie, H. Yang, M. Geng, and J. Liu, “Specific Emitter Identification of Frequency Hopping Signals Based on Feature Extraction and Deep Residual Network,” IEEE Access, vol. 10, pp. 119084–119094, 2022, doi: 10.1109/ACCESS.2022.3221432.
26. [26] C. Zhu, L. Liu, and X. Peng, “Specific Emitter Identification Based on Temporal Convolutional Network Sequence Processing,” IEEE Commun. Lett., vol. 27, no. 10, pp. 2667–2671, Oct. 2023, doi: 10.1109/LCOMM.2023.3312390.
27. [27] R. Fan, C. Si, Y. Han, and Q. Wan, “RFFsNet-SEI: A Multidimensional Balanced-RFFs Deep Neural Network Framework for Specific Emitter Identification,” J. Syst. Eng. Electron., vol. 35, no. 3, pp. 558–574, Jun. 2024, doi: 10.23919/JSEE.2023.000069.
28. [28] Z.-M. Liu, “Multi-feature fusion for specific emitter identification via deep ensemble learning,” Digit. Signal Process., vol. 110, p. 102939, Mar. 2021, doi: 10.1016/j.dsp.2020.102939.
29. [29] W. Guo, J. Wang, and S. Wang, “Deep Multimodal Representation Learning: A Survey,” IEEE Access, vol. 7, pp. 63373–63394, 2019, doi: 10.1109/ACCESS.2019.2916887.
30. [30] J. Genova, Electronic warfare signal processing. in Artech house electronic warfare library. Boston: Artech house, 2018.
31. [31] G. Huang, Y. Yuan, X. Wang, and Z. Huang, “Specific Emitter Identification Based on Nonlinear Dynamical Characteristics,” Can. J. Electr. Comput. Eng., vol. 39, no. 1, pp. 34–41, 2016, doi: 10.1109/CJECE.2015.2496143.
32. [32] Y. He, K. Wang, Q. Song, H. Li, and B. Zhang, “Specific Emitter Identification Algorithm Based on Time–Frequency Sequence Multimodal Feature Fusion Network,” Electronics, vol. 13, no. 18, p. 3703, Sep. 2024, doi: 10.3390/electronics13183703.
33. [33] Z. Zhu, H. Ji, and L. Li, “Deep Multimodal Subspace Interactive Mutual Network for Specific Emitter Identification,” IEEE Trans. Aerosp. Electron. Syst., vol. 59, no. 4, pp. 4289–4300, Aug. 2023, doi: 10.1109/TAES.2023.3240115.
34. [34] D. Lv, Z. Yu, J. Xie, and H. Zhang, “Review on the Development of Few-Shot Specific Emitter Identification Technology,” in 2024 4th International Conference on Electronic Information Engineering and Computer Science (EIECS), Yanji, China: IEEE, Sep. 2024, pp. 1061–1068. doi: 10.1109/EIECS63941.2024.10800029.
35. [35] P. Man, C. Ding, W. Ren, and G. Xu, “A Specific Emitter Identification Algorithm under Zero Sample Condition Based on Metric Learning,” Remote Sens., vol. 13, no. 23, p. 4919, Dec. 2021, doi: 10.3390/rs13234919.
36. [36] J. Liu, J. Wang, H. Huang, and J. Li, “Specific emitter identification unaffected by time through adversarial domain adaptation and continual learning,” Eng. Appl. Artif. Intell., vol. 138, p. 109324, Dec. 2024, doi: