电子学报2025，Vol.53Issue(12)：4527-4540,14.DOI:10.12263/DZXB.20250843
扩散模型驱动的跨时间域通信辐射源个体增量识别方法
A Diffusion Model Driven Approach for Cross-Time-Domain Incremental Specific Emitter Identification
摘要
Abstract
Specific emitter identification(SEI)exploits subtle hardware discrepancies caused by manufacturing im⁃perfections and device aging to perform transmitter identification and attribution at the physical layer.Compared with tradi⁃tional authentication schemes that rely on protocols and cryptographic keys,SEI requires no modification to the protocol stack,is transparent to transmitted data,and incurs low deployment cost,making it valuable for applications such as spec⁃trum regulation,wireless security,cognitive radio,and sensing in complex electromagnetic environments.However,in real-world wireless scenarios,time-varying and scene-dependent channel conditions introduce unstable modulation and distor⁃tion to radio-frequency fingerprints.Effects such as multipath fading,carrier frequency offset,and phase noise drift over time,causing the signals emitted by the same device to exhibit significant temporal variation.As a result,identification per⁃formance degrades markedly in the target domain,posing a major obstacle to practical deployment.To mitigate domain dis⁃tribution shifts,existing studies mainly investigate transfer learning and domain adaptation approaches.Transfer learning re⁃lies on fine-tuning with labeled target-domain data and can improve target-domain performance,but it often disrupts previ⁃ously learned source-domain knowledge and leads to catastrophic forgetting.Unsupervised domain adaptation reduces distri⁃bution discrepancies through feature alignment,pseudo labeling,and entropy minimization;however,due to the absence of explicit supervision,performance improvements are limited,and such methods struggle to handle continuously arriving data in online scenarios.Incremental learning emphasizes balancing adaptation to new data with the preservation of prior knowl⁃edge,yet most existing approaches still require labeled data or additional storage,making them difficult to apply directly to unlabeled cross-time SEI tasks.The advancement of generative modeling provides a new opportunity to address these chal⁃lenges.Diffusion models characterize complex data distributions through forward noise injection and reverse denoising pro⁃cesses,and are well suited for modeling the superposition of channel perturbations and device-intrinsic features,enabling the recovery of radio-frequency fingerprints from distorted observations.Nevertheless,existing studies predominantly focus on denoising or data generation,and have not fully addressed cross-time identification and continual learning requirements.To this end,this paper proposes a diffusion-model-driven cross-time incremental SEI method.In the source domain,for⁃ward diffusion is employed to explicitly model channel perturbations,while in the target domain,reverse diffusion progres⁃sively restores discriminative representations that approximate the source-domain distribution,thereby suppressing feature drift.A cross-attention mechanism is incorporated into the diffusion network to inject emitter identity information during de⁃noising,enhancing inter-class separability.Furthermore,an unsupervised incremental learning strategy is introduced,which achieves continual adaptation using only unlabeled target-domain samples through distribution consistency and knowledge-preservation regularization,effectively mitigating catastrophic forgetting.Cross-time identification experiments on the WiS⁃ig dataset demonstrate that the proposed method improves target-domain identification accuracy by more than 5 percentage points compared with representative domain adaptation methods,and enhances source-domain performance retention by ap⁃proximately 10 percentage points relative to mainstream incremental learning strategies,validating its channel restoration capability,feature alignment effectiveness,and robustness under dynamic channel conditions.关键词
通信辐射源个体识别/跨时间域/扩散模型/增量学习/信号处理/跨注意力机制Key words
specific emitter identification/cross-time domain/diffusion model/incremental learning/signal process⁃ing/cross-attention mechanism分类
信息技术与安全科学引用本文复制引用
赵东兴,刘辉,黄科举,杨俊安..扩散模型驱动的跨时间域通信辐射源个体增量识别方法[J].电子学报,2025,53(12):4527-4540,14.基金项目
国防科技大学青年自主创新科学基金(No.ZK24-44) Independent Scientific Research Program of National University of Defense Technology(No.ZK24-44) （No.ZK24-44）
