Radio frequency fingerprint authentication based on feature fusion and contrastive learning

Radio frequency fingerprints (RFFs) are inherent attributes of wireless devices caused by differences in electronic components, which can serve as unique device identifiers and effective means of achieving physical layer authentication. However, traditional RFF approaches predominantly depend on manual feature extraction, which struggles to effectively distinguish devices due to its limited generalization capability as the number of devices grows. Additionally, current machine learning-based methods are designed for scenarios with a fixed set of trained devices while they fail to handle unknown devices. In this paper, we propose a novel contrastive learning-based RFF authentication framework to address the above challenges. The proposed framework integrates both manual feature extraction and deep learning-based techniques to enhance the generalization ability of RFFs, thereby enabling efficient differentiation among a vast number of devices. To further address the limitations of traditional machine learning approaches in dealing with unknown devices, we incorporate contrastive learning techniques into RFF authentication. By employing an input construction strategy, we generate positive and negative sample pairs of the RFFs to train an RFF compression network, allowing it to learn pivotal features within the fused RFFs. This process results in highly discriminative representations of the fused RFFs, ensuring effective authentication of open-set devices. The experimental results demonstrate that our method achieves an accuracy of 98% in open-set device classification even in the most complex experimental scenario, significantly outperforming other benchmark methods.