Robust Adversarial Attacks on Deep Learning-Based RF Fingerprint Identification
- 21 March 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 12 (6) , 1037-1041
Abstract
Deep learning (DL)-based radio frequency fingerprint identification (RFFI), despite its state-of-the-art capability in improving the security performance of communication networks, is still vulnerable to carefully crafted and imperceptible adversarial attack. However, conventional radio frequency (RF) adversarial attacks ignore the impact of the practical fading channels between the attacker and the sensor. In this letter, a generation adversarial perturbations (GAP) problem is formulated in a DL-based RFFI network. Both the case of ideally perfect channel state information (CSI) and the practical imperfect CSI are considered. The closed-form expression of the adversarial example based on the perfect CSI is provided. In order to address the intractable non-convex robust optimization problem under the imperfect CSI, a spoofing attack algorithm is proposed by exploiting the S-procedure. Simulation results demonstrate that our proposed scheme achieves a superior spoofing ratio compared with other benchmark schemes.Keywords
Funding Information
- National Key Research and Development Program of China (2020YFB1807602)
- National Natural Science Foundation of China (62222107, 62071223, 62031012)
- Young Elite Scientist Sponsorship Program by China Association for Science and Technology
- Basic Research Program for Natural Science of Shaanxi Province of China (2020JQ-851)
- Key Research and Development Project of Shaanxi Province (2023-YBGY-272)
- Key Research and Development Program of Shaanxi in Industrial Domain (2021GY-103)
This publication has 15 references indexed in Scilit:
- The Best Defense Is a Good Offense: Adversarial Attacks to Avoid Modulation DetectionIEEE Transactions on Information Forensics and Security, 2020
- RF-based drone detection and identification using deep learning approaches: An initiative towards a large open source drone databaseFuture Generation Computer Systems, 2019
- Deep Learning Based RF Fingerprint Identification Using Differential Constellation Trace FigureIEEE Transactions on Vehicular Technology, 2019
- RFAL: Adversarial Learning for RF Transmitter Identification and ClassificationIEEE Transactions on Cognitive Communications and Networking, 2019
- Physical Adversarial Attacks Against End-to-End Autoencoder Communication SystemsIEEE Communications Letters, 2019
- Deep Learning Convolutional Neural Networks for Radio IdentificationIEEE Communications Magazine, 2018
- Adversarial Attacks on Deep-Learning Based Radio Signal ClassificationIEEE Wireless Communications Letters, 2018
- Robust AN-Aided Beamforming and Power Splitting Design for Secure MISO Cognitive Radio With SWIPTIEEE Transactions on Wireless Communications, 2017
- Relay authentication by exploiting I/Q imbalance in amplify-and-forward system2014
- Convex Optimization2004