Channel-Distortion-Agnostic Specific Emitter Identification Based on Decentralized Learning

The rapid growth of Internet of Things (IoT) devices poses new challenges for secure and scalable device authentication. Deep learning-based specific emitter identification (SEI) has shown promise by extracting unique features from radio frequency (RF) signals. However, its performance often degrades under varying channel conditions, as models trained on channel-specific data exhibit poor generalization. To address this, we propose a channel-distortion-agnostic SEI framework based on decentralized learning. The method enables multiple distributed clients to collaboratively train a global model without sharing raw RF data, thereby preserving privacy and reducing communication overhead. An adaptive model aggregation strategy is introduced to mitigate client heterogeneity by weighting local updates based on data characteristics. Additionally, we incorporate realistic RF impairments, including DC offset, IQ imbalance, and power amplifier nonlinearity, to simulate practical transmitter conditions. Extensive experiments under diverse wireless channels demonstrate that the proposed approach outperforms baselines, achieving superior accuracy and robustness across heterogeneous environments.