Adversarial Attack Generation Based on Meta Learning in Specific Emitter Identification
- 11 November 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (2) , 285-289
Abstract
Specific emitter identification (SEI) based on deep learning is a highly potential physical layer security authentication technology. However, deep neural networks (DNNs) are vulnerable to adversarial examples. In this letter, we propose an adversarial attack method based on meta-learning strategies (Meta-SA) against SEI. Meta-SA according meta-learning idea to explore the dynamic decision-making of attack perturbation parameters. It can quickly identify the characteristics of the SEI model and evolve defense mechanisms, thus the optimal attack parameters are adjusted to generate new effective attacks. We define the meta model to adjust the attack parameters to maximize the effect of the attack, enhance the attack covertness and improve the overall success rate of the attack. In order to verify the feasibility of Meta-SA, experiments are based on the actual collected signal ADS-B dataset, the results show that Meta-SA has good performance and the high recognition model ResNet accuracy is minimized to 9.51%.Keywords
Funding Information
- National Natural Science Foundation of China (62331010)
- Fundamental Research Funds for the Central Universities through the HEU Project (3072024XX0806)
This publication has 18 references indexed in Scilit:
- Robust and Generalized Physical Adversarial Attacks via Meta-GANIEEE Transactions on Information Forensics and Security, 2023
- Semi-Supervised Specific Emitter Identification Method Using Metric-Adversarial TrainingIEEE Internet of Things Journal, 2023
- Large-scale real-world radio signal recognition with deep learningChinese Journal of Aeronautics, 2022
- Few-Shot Specific Emitter Identification via Deep Metric Ensemble LearningIEEE Internet of Things Journal, 2022
- Threat of Adversarial Attacks on DL-Based IoT Device IdentificationIEEE Internet of Things Journal, 2021
- Physical Adversarial Attacks Against End-to-End Autoencoder Communication SystemsIEEE Communications Letters, 2019
- Specific Emitter Identification via Convolutional Neural NetworksIEEE Communications Letters, 2018
- Adversarial Attacks on Deep-Learning Based Radio Signal ClassificationIEEE Wireless Communications Letters, 2018
- Boosting Adversarial Attacks with Momentum2018
- Over-the-Air Deep Learning Based Radio Signal ClassificationIEEE Journal of Selected Topics in Signal Processing, 2018