Papers
Topics
Authors
Recent
Search
2000 character limit reached

Adversarial Attacks and Defenses for Wireless Signal Classifiers using CDI-aware GANs

Published 30 Nov 2023 in cs.IT, cs.NI, eess.SP, and math.IT | (2311.18820v1)

Abstract: We introduce a Channel Distribution Information (CDI)-aware Generative Adversarial Network (GAN), designed to address the unique challenges of adversarial attacks in wireless communication systems. The generator in this CDI-aware GAN maps random input noise to the feature space, generating perturbations intended to deceive a target modulation classifier. Its discriminators play a dual role: one enforces that the perturbations follow a Gaussian distribution, making them indistinguishable from Gaussian noise, while the other ensures these perturbations account for realistic channel effects and resemble no-channel perturbations. Our proposed CDI-aware GAN can be used as an attacker and a defender. In attack scenarios, the CDI-aware GAN demonstrates its prowess by generating robust adversarial perturbations that effectively deceive the target classifier, outperforming known methods. Furthermore, CDI-aware GAN as a defender significantly improves the target classifier's resilience against adversarial attacks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (16)
  1. B. Biggio, I. Corona, D. Maiorca, B. Nelson, N. Šrndić, P. Laskov, G. Giacinto, and F. Roli, “Evasion attacks against machine learning at test time,” in ECML PKDD, 2013.
  2. I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” in ICLR, 2015.
  3. D. Adesina, C.-C. Hsieh, Y. E. Sagduyu, and L. Qian, “Adversarial machine learning in wireless communications using RF data: A review,” IEEE Communications Surveys & Tutorials, 2022.
  4. S. Sinha and A. Soysal, “Channel aware adversarial attacks are not robust,” in IEEE MILCOM, 2023.
  5. B. Flowers, R. M. Buehrer, and W. C. Headley, “Evaluating adversarial evasion attacks in the context of wireless communications,” IEEE Trans. on Information Forensics and Security, vol. 15, pp. 1102–1113, 2019.
  6. Y. Lin, H. Zhao, Y. Tu, S. Mao, and Z. Dou, “Threats of Adversarial Attacks in DNN-based modulation recognition,” in IEEE INFOCOM, 2020.
  7. M. Sadeghi and E. G. Larsson, “Adversarial attacks on deep-learning based radio signal classification,” IEEE Wireless Communications Letters, vol. 8, no. 1, pp. 213–216, 2018.
  8. 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. on Wireless Communications, vol. 21, no. 6, pp. 3868–3880, 2021.
  9. A. Bahramali, M. Nasr, A. Houmansadr, D. Goeckel, and D. Towsley, “Robust adversarial attacks against DNN-based wireless communication systems,” in ACM SIGSAC, 2021.
  10. M. Z. Hameed, A. György, and D. Gündüz, “The best defense is a good offense: Adversarial attacks to avoid modulation detection,” IEEE Trans. on Information Forensics and Security, vol. 16, pp. 1074–1087, 2020.
  11. Y. Shi, Y. E. Sagduyu, T. Erpek, and M. C. Gursoy, “How to attack and defend Next G radio access network slicing with reinforcement learning,” IEEE Open Journal of Vehicular Technology, vol. 4, pp. 181–192, 2022.
  12. Y. Shi and Y. E. Sagduyu, “Adversarial machine learning for flooding attacks on 5G radio access network slicing,” in ICC Workshops, 2021.
  13. Y. Siriwardhana, P. Porambage, M. Liyanage, and M. Ylianttila, “AI and 6G security: Opportunities and Challenges,” in EuCNC/6G Summit, 2021.
  14. Z. Luo, S. Zhao, Z. Lu, J. Xu, and Y. E. Sagduyu, “When attackers meet AI: Learning-empowered attacks in cooperative spectrum sensing,” IEEE Trans. on Mobile Computing, vol. 21, no. 5, pp. 1892–1908, 2020.
  15. T. J. O’Shea and N. West, “Radio machine learning dataset generation with gnu radio,” in Proceedings of the GNU Radio Conference, 2016.
  16. T. O’Shea and J. Hoydis, “An introduction to deep learning for the physical layer,” IEEE Trans. on Cognitive Communications and Networking, vol. 3, no. 4, pp. 563–575, 2017.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Authors (2)

Collections

Sign up for free to add this paper to one or more collections.