# A Self-Supervised Specific Emitter Identification Method Based on Contrastive Asymmetric Masked Learning

## TL;DR

This paper introduces a new self-supervised method for identifying wireless emitters using contrastive learning, which works well even with limited labeled data.

## Contribution

The novel CAML-SEI method uses asymmetric masked learning and contrastive loss to improve emitter identification with few labeled samples.

## Key findings

- CAML-SEI outperforms existing SEI methods in real-world ADS-B and Wi-Fi datasets.
- The method effectively learns generalized radio frequency fingerprint features with limited labeled data.
- Contrastive loss enhances feature discriminability by aggregating positive and separating negative samples.

## Abstract

Specific emitter identification (SEI) is a core technology for wireless device security that plays a crucial role in protecting wireless communication systems from various security threats. However, current deep learning-based SEI methods heavily rely on large amounts of labeled data for supervised training, facing challenges in non-cooperative communication scenarios. To address these issues, this paper proposes a novel contrastive asymmetric masked learning-based SEI (CAML-SEI) method, effectively solving the problem of SEI under scarce labeled samples. The proposed method constructs an asymmetric auto-encoder architecture, comprising an encoder network based on channel squeeze-and-excitation residual blocks to capture radio frequency fingerprint (RFF) features embedded in signals, while employing a lightweight single-layer convolutional decoder for masked signal reconstruction. This design promotes the learning of fine-grained local feature representations. To further enhance feature discriminability, a learnable non-linear mapping is introduced to compress high-dimensional encoded features into a compact low-dimensional space, accompanied by a contrastive loss function that simultaneously achieves feature aggregation of positive samples and feature separation of negative samples. Finally, the network is jointly optimized by combining signal reconstruction and feature contrast tasks. Experiments conducted on real-world ADS-B and Wi-Fi datasets demonstrate that the proposed method effectively learns generalized RFF features, and the results show superior performance compared with other SEI methods.