IEEE Signal Processing Letters · 2023 · 47 citations · 18 references
ComputingComputer ScienceCybersecurityFeature EngineeringMachine LearningWireless SecurityDeep LearningOptimization For Machine LearningPattern RecognitionPhysical Layer SecurityRadio Frequency SecurityUnsupervised LearningContrastive LearningFeature TransferFingerprint ExtractionIdentificationPerformance DegradationPhysical Layer AuthenticationRadio Frequency FingerprintingRadio-frequency Identification
Radio frequency fingerprint (RFF) identification is emerging as an attractive paradigm for physical layer security. Despite the exceptional accuracy achieved by deep learning (DL) based schemes, few works consider the cross-receiver scenario. The performance deteriorates significantly when the model is deployed on new receivers directly. To this end, a cross-receiver RFF learning scheme is proposed. First, an unsupervised pre-training method based on contrastive learning is utilized to extract receiver-agnostic features. Then, the model is optimized by subdomain adaptation to further improve identification performance. The proposed scheme does not require multiple labeled datasets from different receivers. And experimental results indicate that the proposed scheme effectively alleviates performance degradation in the cross-receiver scenario.
18
Exploring Simple Siamese Representation Learning
Xinlei Chen, Kaiming He · 2021 · 3.3K citations
Integrating structured biological data by Kernel Maximum Mean Discrepancy
Karsten Borgwardt, Arthur Gretton, Malte J. Rasch et al. · Bioinformatics · 2006 · 1.7K citations · Full text