Cost-Effective RF Fingerprinting Based on Hybrid CVNN-RF Classifier With Automated Multidimensional Early-Exit Strategy
- 19 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (20) , 32557-32571
Abstract
While the Internet of Things (IoT) technology is booming and offers huge opportunities for information exchange, it also faces unprecedented security challenges. As an important complement to the physical-layer security technologies for IoT, radio frequency fingerprinting (RFF) is of great interest due to its difficulty in counterfeiting. Recently, many machine learning (ML)-based RFF algorithms have emerged. In particular, deep learning (DL) has shown great benefits in automatically extracting complex and subtle features from raw data with high-classification accuracy. However, DL algorithms face the computational cost problem as the difficulty of the RFF task and the size of the deep neural network have increased dramatically. To address the above challenge, this article proposes a novel cost-effective early-exit neural network consisting of a complex-valued neural network (CVNN) backbone with multiple random forest branches, called hybrid CVNN-RF. Unlike conventional studies that use a single fixed DL model to process all radio frequency (RF) samples, our hybrid CVNN-RF considers differences in the recognition difficulty of RF samples and introduces an early-exit mechanism to dynamically process the samples. When processing “easy” samples that can be well classified with high confidence, the hybrid CVNN-RF can end early at the random forest branch to reduce computational cost. Conversely, subsequent network layers will be activated to ensure accuracy. To further improve the early-exit rate, an automated multidimensional early-exit strategy is proposed to achieve scheduling control from multiple dimensions within the network depth and classification category. Finally, our experiments on the public ADS-B data set show that the proposed algorithm can reduce the computational cost by 83% while improving the accuracy by 1.6% under a classification task with 100 categories.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62171110)
This publication has 29 references indexed in Scilit:
- Attention is Needed for RF FingerprintingIEEE Access, 2023
- A comprehensive survey on radio frequency (RF) fingerprinting: Traditional approaches, deep learning, and open challengesComputer Networks, 2022
- Large-scale real-world radio signal recognition with deep learningChinese Journal of Aeronautics, 2022
- Identity Mappings in Deep Residual Networks2016
- Random forest in remote sensing: A review of applications and future directionsISPRS Journal of Photogrammetry and Remote Sensing, 2016
- Device Fingerprinting in Wireless Networks: Challenges and OpportunitiesIEEE Communications Surveys & Tutorials, 2015
- Non-parametric feature generation for RF-fingerprinting on ZigBee devices2015
- RF fingerprint extraction from the energy envelope of an instantaneous transient signal2012
- Wireless security through RF fingerprintingCanadian Journal of Electrical and Computer Engineering, 2007
- ‘Chirplets’ and ‘warblets’: novel time–frequency methodsElectronics Letters, 1992