Cross-Domain Specific Emitter Identification Based on Domain-Specific Classifier

• Published in: IEEE internet of things journal Vol. 12; no. 14; pp. 27660 - 27670
• Main Authors: Xiao, Zhiling, Xie, Yunhong, Li, Qiang, Sun, Guomin, Shao, Huaizong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 15.07.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Classification tree analysis; Cross-domain; Distortion; domain-adapted classifier; Dynamic characteristics; Emitters; Feature extraction; Hardware; Identification; Internet of Things; Machine learning; Receivers; Security; specific emitter identification (SEI); Target recognition; Training; Transforms
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2025.3563894

Specific emitter identification (SEI) is crucial in the Internet of Things (IoT) to ensure the authentication and security of devices. With advancements in deep learning (DL), SEI for IoT devices has achieved remarkable progress. However, traditional DL-based SEI relies on a blanket assumption that emitter signals are transmitted in a constant channel environment and collected by a fixed receiver before identification. This assumption overlooks the dynamic characteristics of real-world IoT scenarios, where the channel environment and receiver are subject to change. Such variations can significantly impact SEI systems, potentially leading to a substantial decrease in identification accuracy. This challenge is known as the cross-domain SEI problem, where different receivers and channel environments are viewed as distinct domains. To mitigate this issue, we integrate unsupervised domain adaptation (UDA) into SEI. We propose an innovative UDA framework named domain-specific classifier network (DSCN) for cross-domain SEI. In our method, we initially use a weight-shared extractor for feature extraction. Unlike most existing UDA methods, we do not enforce the extractor to generate domain-invariant features for cross-domain identification. Instead, we design domain-specific classifiers to process features from different domains: source signal features are recognized by a source-specific classifier, while target signal features are recognized by a target-specific classifier. Experimental results demonstrate that the DSCN framework effectively mitigates identification accuracy degradation in cross-domain scenarios and outperforms existing UDA methods.