Search

Radio frequency fingerprint identification (RFFI) is an emerging device authentication technique, which exploits the hardware characteristics of the RF front-end as device identifiers. The receiver hardware impairments interfere with the feature extraction of transmitter impairments, but their effect and mitigation have not been comprehensively studied. In this paper, we propose a receiver-agnostic RFFI system by employing adversarial training to learn the receiver-independent features. Moreover, when there are multiple receivers, collaborative inference are designed to enhance classification accuracy. Finally, we show how it is possible to leverage fine-tuning for further improvement with fewer collected signals. To validate the approach, we have conducted extensive experimental evaluation by applying the approach to a LoRaWAN case study involving ten LoRa devices and 20 software-defined radio (SDR) receivers. The results show that receiver-agnostic training enables the trained neural network to become robust to changes in receiver characteristics. The collaborative inference improves classification accuracy by up to 20% beyond a single-receiver RFFI system and fine-tuning can bring a 40% improvement for underperforming receivers. The system is further evaluated on a more practical testbed. By making additional use of online augmentation and multi-packet inference, the identification accuracy is improved from 50% to 90% at 10 dB.

Wi-Fi sensing can classify human activities because each activity causes unique changes to the channel state information (CSI). Existing WiFi sensing suffers from limited scalability as the system needs to be retrained whenever new classes are added, which causes overheads of data collection and retraining. Cross-domain sensing may fail because the mapping between activities and CSI variations is destroyed when a different environment or user (domain) is involved. This paper proposed a few-shot learning-based WiFi sensing system, named FewSense, which can recognise novel classes in unseen domains with only a few samples. Specifically, a feature extractor was pre-trained offline using the source domain data. When the system was applied in the target domain, a few samples were used to fine-tune the feature extractor for domain adaptation. Inference was made by computing the cosine similarity. FewSense can further boost the classification accuracy by collaboratively fusing inference from multiple receivers. We evaluated the performance of FewSense using three public datasets, i.e., SignFi, Widar, and Wiar. The results show that FewSense with five-shot learning recognised novel classes in unseen domains with an accuracy of 93.9%, 96.5%, and 82.7% on the SignFi, Widar, and Wiar datasets, respectively. Our collaborative sensing model improved system performance by an average of 29.2%.