5 March 2026 in IEEE Transactions on Information Forensics and Security
Specific emitter identification (SEI) separates the radio frequency fingerprint (RFF) from signals, which is of great significance in solving Internet of Things (IoT) security problems. However, the scarcity of high-quality, diverse, and labeled data in real-world scenarios limits the application of SEI. Under such conditions, the SEI is referred to as few-shot SEI (FS-SEI). To surmount this challenge, we propose a diffusion model-based data augmentation method capable of generating a substantial volume of diverse, high-quality data. Specifically, we develop a multi-scale convolutional block attention module denoising diffusion probabilistic model (MSCBAM-DDPM), which enhances feature capture capabilities, laying the foundation for the generation of diverse data. Furthermore, we propose an adaptive two-stage multi-domain loss function that guides the model to learn the characteristics of the original data and further derive other similar features, thereby achieving the goal of generating diverse and high-quality data. Finally, we theoretically derive the feasibility of the proposed loss function and further demonstrate the excellent diversity and quality of the data generated by our method, as well as its considerable gain for FS-SEI, through extensive experiments on real-world signal datasets.
13 May 2025 in IEEE Wireless Communications Letters
Specific Emitter Identification (SEI) plays a vital role in the fields of electromagnetic spectrum management and electronic warfare. However, existing SEI algorithms typically require labeled information, which is often unavailable in non-cooperative communication and untrusted scenarios. To tackle these challenges, we propose an algorithm based on multi-scale feature adaptive fusion contrastive learning (MSFAF-CL) for unsupervised recognition. First, a contrastive learning network framework capable of extracting multi-scale features (MSF) of signals is designed. Then, an adaptive feature fusion (AFF) module is introduced to better assign weights to different features, thereby enhancing classification performance. When constructing positive and negative sample pairs for signals, we analyze the limitations of commonly used signal augmentation techniques and propose an algorithm that uses the signal’s In-phase and Quadrature (I/Q) sequence to construct positive and negative sample pairs directly. Extensive experimental results based on the Automatic Dependent Surveillance-Broadcast (ADS-B) individual signal dataset demonstrate that the proposed algorithm can effectively distinguish individual signals under unsupervised conditions, achieving a high recognition rate on a 15-category signal dataset. Furthermore, the algorithm is more efficient compared with the state-of-the-art algorithms.
14 March 2025 in IEEE Transactions on Cognitive Communications and Networking
Specific emitter identification (SEI) is considered an effective technical means to protect wireless networks from malicious intrusion, which identifies and classifies devices through radio frequency fingerprints (RFF) generated by hardware defects in transmitters. However, the differences between individual transmitters of the same type are extreme subtle, and the features available to distinguish them are extremely limited and fragile. This susceptibility to noise interference greatly affects the identification of transmitters. To address this issue, we propose a deep learning (DL) model that operates in the complex signals capable of extracting features from multiple domains and optimize the distribution of signals from different transmitters in the feature space to maximize the utilization of limited features. Specifically, in this paper, we introduce the U-fusion Transformer (UFformer) for efficient integration of multi-domain signals features, along with adaptive labels-directed softmax (ALD_Softmax) to optimize the backpropagation process, thereby reducing intra-class distances and increasing inter-class distances of radiation source signals to enhance classifier performance. Experimental results on real-world data demonstrate that our proposed model outperforms current SEI methods in terms of training cycles, recognition accuracy, and robustness.
5 June 2025 in IEEE Transactions on Cognitive Communications and Networking
In wireless communication networks, the abundance of electromagnetic devices poses a significant challenge to the security of electromagnetic space. The emergence of automatic modulation classification (AMC) has provided significant support for electromagnetic spectrum management. However, varying environments can lead to alterations in signal distributions, the potential presence of unknown modulation signals and number of types also bring hurdles for regulation. In response, this paper proposes a Transformer-based Generative Adversarial Network (TA-ClusterGAN) incorporating Infinite Gaussian Mixture Model for AMC (TIGM-AMC) algorithm, capable of clustering signals under the conditions of unknown label and number of types. We innovatively introduce the Adversarial Chinese Restaurant Process (ACPR) to infer the number of modulation categories in AMC, leverage contour stellar image (CSI) technology to transform signals into graph domain and enhance clustering effectiveness through attention mechanism. Under the condition that the number of modulation classes is unknown, the model undergoes pre-training first, then we map the category vectors output by the encoder into an infinite gaussian space. Results show that TA-ClusterGAN can achieve 98.71% NMI when the number of modulation classes is known. And we can accurately infer the number of modulation types through TIGM-AMC when the number of categories is unknown, which approach can enhance the adaptability of AMC in unknown environments.