AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Tsinghua Science and Technology Article
PDF (2.9 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

Deep Time-Frequency Denoising Transform Defense for Spectrum Monitoring in Integrated Networks

College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
School of Electronic Information, Wuhan University, Wuhan 430072, China
Show Author Information

Abstract

The Space-Air-Ground-Sea Integrated Networks (SAGSIN) significantly enhance global communication by merging satellite, aviation, terrestrial, and marine networks. Crucial to SAGSIN’s functionality and security is spectrum monitoring using deep learning-based Automatic Modulation Classification (AMC), essential for processing and classifying complex modulation signals. However, these AMC models are susceptible to adversarial attacks. Thus, we introduce the Deep Time-Frequency Denoising Transformation (DTFDT) defense method to mitigate the impact of adversarial attacks. The DTFDT method is comprised of a deep denoising module and a transformation module. The denoising module maps signals into the time-frequency domain, amplifying the differences between benign and adversarial examples, aiding in the elimination of adversarial perturbations. Concurrently, the transformation module develops a learnable network, generating example-specific transformation matrices suited for signal data, which diminishes the effectiveness of attacks. Extensive evaluations on two datasets, RML2016.10a and DMRadio09.real, demonstrate the superior defense capabilities of DTFDT against various attacks.

Keywords

Space-Air-Ground-Sea Integrated Networks (SAGSIN)spectrum monitoringadversarial defenseDeep Time-Frequency Denoising Transformation (DTFDT)transformation module

References

[1]

J. Xu, M. A. Kishk, and M.-S. Alouini, Space-air-ground-sea integrated networks: Modeling and coverage analysis, IEEE Trans. Wirel. Commun., vol. 22, no. 9, pp. 6298–6313, 2023.
Crossref Google Scholar
[2]
Y. Gang, Y. Zhang, and Z. Zhuo, Joint task offloading and resource allocation strategy for space-air-ground integrated vehicular networks, Tsinghua Science and Technology, doi: 10.26599/TST.2024.9010055.
Crossref
[3]

M. A. Khan, B. A. Alzahrani, A. Barnawi, A. Al-Barakati, A. Irshad, and S. A. Chaudhry, A resource friendly authentication scheme for space-air-ground-sea integrated maritime communication network, Ocean Eng., vol. 250, p. 110894, 2022.
Crossref Google Scholar
[4]

P. P. Ray, A review on 6G for space-air-ground integrated network: Key enablers, open challenges, and future direction, J. King Saud Univ-Com, vol. 34, no. 9, pp. 6949–6976, 2022.
Crossref Google Scholar
[5]
J. Chen, H. Zhang, and Z. Xie, Space-Air-Ground Integrated Network (SAGIN): A survey, arXiv preprint arXiv: 2307.14697, 2023.
[6]

S. Peng, S. Sun, and Y.-D. Yao, A survey of modulation classification using deep learning: Signal representation and data preprocessing, IEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 12, pp. 7020–7038, 2022.
Crossref Google Scholar
[7]

C. Liu, X. Fu, Y. Wang, L. Guo, Y. Liu, Y. Lin, H. Zhao, and G. Gui, Overcoming data limitations: A few-shot specific emitter identification method using self-supervised learning and adversarial augmentation, IEEE Trans. Inf. Forensics Secur., vol. 19, pp. 500–513, 2023.
Crossref Google Scholar
[8]

F. Liu, Z. Zhang, and R. Zhou, Automatic modulation recognition based on CNN and GRU, Tsinghua Science and Technology, vol. 27, no. 2, pp. 422–431, 2022.
Crossref Google Scholar
[9]

T. Balachander, K. Ramana, R. M. Mohana, G. Srivastava, and T. R. Gadekallu, Cooperative spectrum sensing deployment for cognitive radio networks for internet of things 5G wireless communication, Tsinghua Science and Technology, vol. 29, no. 3, pp. 698–720, 2024.
Crossref Google Scholar
[10]

P. Zhang, N. Chen, S. Shen, S. Yu, N. Kumar, and C.-H. Hsu, AI-enabled space-air-ground integrated networks: Management and optimization, IEEE Netw., vol. 38, no. 2, pp. 186–192, 2024.
Crossref Google Scholar
[11]
C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus, Intriguing properties of neural networks, in Proc. International Conference on Learning Representations, Vienna, Austria, 2014, pp. 1035–1045.
[12]

M. Sadeghi and E. G. Larsson, Physical adversarial attacks against end-to-end autoencoder communication systems, IEEE Commun. Lett., vol. 23, no. 5, pp. 847–850, 2019.
Crossref Google Scholar
[13]

D. Adesina, C.-C. Hsieh, Y. E. Sagduyu, and L. Qian, Adversarial machine learning in wireless communications using RF data: A review, IEEE Commun. Surv. Tutor., vol. 25, no. 1, pp. 77–100, 2023.
Crossref Google Scholar
[14]

S. Zheng, L. Ye, X. Wang, J. Chen, H. Zhou, C. Lou, Z. Zhao, and X. Yang, Primary user adversarial attacks on deep learning-based spectrum sensing and the defense method, China Commun., vol. 18, no. 12, pp. 94–107, 2021.
Crossref Google Scholar
[15]
D. Zhou, N. Wang, C. Peng, X. Gao, X. Wang, J. Yu, and T. Liu, Removing adversarial noise in class activation feature space, in Proc. IEEE Int. Conf. Computer Vision (ICCV), Montreal, Canada, 2021, pp. 7878–7887.
Crossref
[16]
Y. Zheng, L. Qi, Z. Bao, J. Fu, and H. Jiang, MDPD: Mapping-based data processing defense against adversarial attacks in automatic modulation classification, in Proc. IEEE INFOCOM 2023−IEEE Conf. Comput. Commun. Workshops, Hoboken, NJ, USA, 2023, pp. 1–6.
Crossref
[17]

J. Li, S. Zhang, J. Cao, and M. Tan, Learning defense transformations for counterattacking adversarial examples, Neural Netw., vol. 164, pp. 177–185, 2023.
Crossref Google Scholar
[18]

B. Kim, Y. E. Sagduyu, K. Davaslioglu, T. Erpek, and S. Ulukus, Channel-aware adversarial attacks against deep learning-based wireless signal classifiers, IEEE Trans. Wirel. Commun., vol. 21, no. 6, pp. 3868–3880, 2022.
Crossref Google Scholar
[19]
B. Kim, Y. E. Sagduyu, T. Erpek, K. Davaslioglu, and S. Ulukus, Adversarial attacks with multiple antennas against deep learning-based modulation classifiers, in Proc. 2020 IEEE Globecom Workshops (GC Wkshps), Taipei, China, 2020, pp. 1–6.
Crossref
[20]
S. Zhang, J. Yu, Z. Bao, S. Mao, and Y. Lin, Spectrum focused frequency adversarial attacks for automatic modulation classification, IEEE Trans. Cogn. Commun. Netw., doi: 10.1109/TCCN.2024.3382126.
Crossref
[21]
Y. Lin, H. Zhao, Y. Tu, S. Mao, and Z. Dou, Threats of adversarial attacks in DNN-based modulation recognition, in Proc. IEEE INFOCOM 2020 IEEE Conf. Comput. Commun., Virtual Event, 2020, pp. 2469–2478.
Crossref
[22]

Y. Lin, H. Zhao, X. Ma, Y. Tu, and M. Wang, Adversarial attacks in modulation recognition with convolutional neural networks, IEEE Trans. Rel., vol. 70, no. 1, pp. 389–401, 2021.
Crossref Google Scholar
[23]
I. J. Goodfellow, J. Shlens, and C. Szegedy, Explaining and harnessing adversarial examples, arXiv preprint arXiv: 1412.6572, 2014.
[24]
A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu, Towards deep learning models resistant to adversarial attacks, arXiv preprint arXiv: 1706.06083, 2017.
[25]
A. Kurakin, I. J. Goodfellow, and S. Bengio, Adversarial examples in the physical world, in Proc. Artif. Intell. Saf. Secur., London, UK, 2018, pp. 99–112.
Crossref
[26]
S. Kokalj-Filipovic, R. Miller, and J. Morman, Targeted adversarial examples against RF deep classifiers, in Proc. ACM Workshop Wireless Security and Machine Learning (WiseML), New York, NY, USA, 2019, p. 6–11.
Crossref
[27]
N. Carlini and D. Wagner, Towards evaluating the robustness of neural networks, in Proc. IEEE Symp. Security Privacy, SanJose, CA, USA, 2017, pp. 39–57.
Crossref
[28]

K. W. McClintick, J. Harer, B. Flowers, W. C. Headley, and A. M. Wyglinski, Countering physical eavesdropper evasion with adversarial training, IEEE Open J. Commun. Soc., vol. 3, pp. 1820–1833, 2022.
Crossref Google Scholar
[29]
S. Zhang, J. Liu, Z. Bao, S. Yu, and Y. Lin, Adversarial domain generalization defense for automatic modulation classification, in Proc. Int. Conf. Communications China (ICCC), Dalian, China, 2023, pp. 1–6.
Crossref
[30]

Q. Tian, S. Zhang, S. Mao, and Y. Lin, Adversarial attacks and defenses for digital communication signals identification, Digit. Commun. Netw., doi: 10.1016/j.dcan.2022.10.010.
Crossref Google Scholar
[31]
C. Guo, M. Rana, M. Cisse, and L. van der Maaten, Countering adversarial images using input transformations, arXiv preprint arXiv: 1711.00117, 2017.
[32]

M. Portnoff, Time-frequency representation of digital signals and systems based on short-time fourier analysis, IEEE Trans. Acoust., Speech, Signal Process., vol. 28, no. 1, pp. 55–69, 1980.
Crossref Google Scholar
[33]
J. Wang, Y. Chen, W. Feng, H. Yu, M. Huang, and Q. Yang, Transfer learning with dynamic distribution adaptation, ACM Trans. Intell. Syst. Technol., vol. 11, no. 1, 2020.
Crossref
[34]
T. J. O’shea, J. Corgan, and T. C. Clancy, Convolutional radio modulation recognition networks, Eng. Appl. Artif. Intell., vol. 629, pp. 213–226, 2016.
Crossref
[35]
H. Zhao, Y. Lin, S. Gao, and S. Yu, Evaluating and improving adversarial attacks on DNN-based modulation recognition, in Proc. IEEE Global Communications Conf. (GLOBECOM), Taipei, China, 2020, pp. 1–5.
Crossref
Tsinghua Science and Technology
Volume 30 Issue 2,
April 2025
Pages 851-863
DOI: 10.26599/TST.2024.9010045
Cite this article:
Zhang S, Yang Y, Yang S, et al. Deep Time-Frequency Denoising Transform Defense for Spectrum Monitoring in Integrated Networks. Tsinghua Science and Technology, 2025, 30(2): 851-863. https://doi.org/10.26599/TST.2024.9010045

80

Views

4

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 14 December 2023
Revised: 10 February 2024
Accepted: 28 February 2024
Published: 09 December 2024
© The Author(s) 2025.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Return