Radio frequency fingerprint identification (RFFI) offers a promising physical-layer method to authenticate devices based on unique hardware impairments. However, existing RFFI systems use deep learning (DL) models that are resource- intensive. Training is particularly demanding, requiring repeated updates to a large number of parameters. In this paper, we introduce a quantum-assisted training (QAST) framework to address training inefficiencies in RFFI. QAST integrates a quantum neural network (QNN) with a mapping network to generate parameters for a classical DL model. This indirect training strategy substantially reduces the number of trainable parameters and the overall memory requirements compared to direct training of the DL model. We achieve this by introducing a multimodal mapping network that effectively learns the QNN output. This network generates multiple classical parameters from a shared quantum representation, thereby reducing qubit requirements and lowering the risk of barren-plateau-related trainability degradation. We also propose a new embedding method that reduces the size of the embedding matrix and yields a 15% to 30% reduction in training time. The tailored QAST framework trains the RFFI model while requiring only 10% of the original number of parameters while maintaining comparable accuracy, thereby substantially reducing memory and computational overhead and enabling efficient training or retraining in resource-limited environments.

Radio frequency fingerprint identification is a promising technique for device authentication that relies on the unique radio frequency fingerprint features caused by hardware impairments. Existing radio frequency fingerprint identification models usually contain a significant number of trainable parameters, making them undesirable for Internet of Things applications. In this paper, we augment a classical neural network by introducing an intermediary quantum neural network stage to enhance the authentication of Internet of Things devices using radio frequency fingerprint features. The model is based on the combination of quantum and classical machine learning and benefits from a significantly smaller number of trainable parameters. Empirical results show that our proposed model not only achieves a much smaller footprint (in terms of device memory) but also delivers competitive accuracy to conventional deep learning approaches. It therefore shows much promise as a solution for securing networks which feature resource-constrained Internet of Things devices.