Adversarial Transfer Attack Against and Adaptive Defense for Intelligent Modulation Recognition
- 16 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 4018-4031
Abstract
Deep learning (DL) can enhance automatic modulation recognition in complex wireless communication environments by greatly improving the efficiency and accuracy of modulation recognition. However, the DL-based intelligent recognition model also has great vulnerability to the adversarial attack. To avoid this, a subtle adversarial perturbation can be added to the signal to disrupt the eavesdropper’s modulation recognition model while ensuring the normal demodulation at the receiving end. However, the transferability of existing attacks is weak, and it is difficult to disrupt the target model while ensuring concealment. This paper proposes a meta adversarial transfer attack method by using meta-training and meta-testing to enhance the transferability of adversarial attacks. In addition, for the transfer attack, this paper proposes an adversarial domain adaptation defense method, which uses the multi-class domain-invariant features of the examples in the source domain and the adversarial domain to improve the robustness of the model against attacks. Simulation results show that, compared with the traditional methods, the proposed attack method has better transferability for the eavesdropper’s model, and that the proposed defense method has better defense against the transfer attack.Keywords
Funding Information
- National Natural Science Foundation of China (U2441250)
- National Natural Science Foundation of China (62231027)
- Natural Science Basic Research Program of Shaanxi (2024JC-JCQN-63)
- Guangxi Key Research and Development Program (2022AB46002)
- Innovation Capability Support Program of Shaanxi (2024RSCXTD-01)
- Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University (YJSJ25007)
This publication has 49 references indexed in Scilit:
- Blockchain and timely auction mechanism-based spectrum managementFuture Generation Computer Systems, 2025
- Intelligent integrated sensing and communication: a surveyScience China Information Sciences, 2024
- Transferable Attacks on Deep Learning Based Modulation Recognition in Cognitive Radio2023
- Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability2022
- Meta Gradient Adversarial Attack2021
- Evaluating and Improving Adversarial Attacks on DNN-Based Modulation Recognition2020
- High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks2020
- Boosting Adversarial Attacks with Momentum2018
- Deep neural network architectures for modulation classification2017
- Convolutional Radio Modulation Recognition Networks2016