Channel-Robust RF Fingerprint Identification Using Multi-Task Learning and Receiver Collaboration
- 12 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 2510-2514
Abstract
Robust radio frequency fingerprint identification (RFFI) is crucial for physical layer authentication, while it suffers from channel effects and requires extra overhead to increase recognition accuracy (RA). To address this, an efficient channel-robust RFFI scheme is proposed, employing a specialized multi-task learning (MTL) framework to direct the neural network (NN) toward extracting channel-robust features. In addition, receiver collaboration (RC) is utilized for data augmentation and output calibration. Experimental results demonstrate that the RA is significantly increased from 51.72% to 99.97% when using the open-resource Wi-Fi signal datasets collected from different time periods. Meanwhile, the requirements for extra data transmission, NN structure, and feature crafting in the inferring stage are dramatically simplified.Keywords
Funding Information
- National Natural Science Foundation of China (62371281)
- China Aeronautical Science Fund (2022Z066057002)
- Open Projects of Guangxi Key Laboratory of Digital Infrastructure
- Guangxi Information Center, Nanning, China (GXDIOP2023011)
- Henan Key Laboratory of Visible Light Communications (HKLVLC2023-B09)
This publication has 14 references indexed in Scilit:
- Radio frequency fingerprint extraction and authentication towards open set in noisy channelsDigital Signal Processing, 2023
- Radio frequency fingerprint identification for Internet of Things: A surveySecurity and Safety, 2023
- Integration of Device Fingerprint Authentication and Physical-Layer Secret Key GenerationIEEE Signal Processing Letters, 2023
- Design of a Channel Robust Radio Frequency Fingerprint Identification SchemeIEEE Internet of Things Journal, 2022
- Multi-task learning approach for modulation and wireless signal classification for 5G and beyond: Edge deployment via model compressionPhysical Communication, 2022
- WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF FingerprintingIEEE Access, 2022
- A Robust Radio-Frequency Fingerprint Extraction Scheme for Practical Device RecognitionIEEE Internet of Things Journal, 2021
- Exposing the Fingerprint: Dissecting the Impact of the Wireless Channel on Radio Fingerprinting2020
- Design of a Hybrid RF Fingerprint Extraction and Device Classification SchemeIEEE Internet of Things Journal, 2018
- Deep Learning for RF Device Fingerprinting in Cognitive Communication NetworksIEEE Journal of Selected Topics in Signal Processing, 2018