Search Results for author: Guanxiong Shen

Found 6 papers, 0 papers with code

Towards Length-Versatile and Noise-Robust Radio Frequency Fingerprint Identification

no code implementations6 Jul 2022 Guanxiong Shen, Junqing Zhang, Alan Marshall, Mikko Valkama, Joseph Cavallaro

During the inference, a multi-packet inference approach is further leveraged to improve the classification accuracy in low SNR scenarios.

Data Augmentation

Towards Receiver-Agnostic and Collaborative Radio Frequency Fingerprint Identification

no code implementations6 Jul 2022 Guanxiong Shen, Junqing Zhang, Alan Marshall, Roger Woods, Joseph Cavallaro, Liquan Chen

In this paper, we propose a receiver-agnostic RFFI system that is not sensitive to the changes in receiver characteristics; it is implemented by employing adversarial training to learn the receiver-independent features.

Collaborative Inference

FewSense, Towards a Scalable and Cross-Domain Wi-Fi Sensing System Using Few-Shot Learning

no code implementations3 Mar 2022 Guolin Yin, Junqing Zhang, Guanxiong Shen, Yingying Chen

When the system was applied in the target domain, few samples were used to fine-tune the feature extractor for domain adaptation.

Domain Adaptation Few-Shot Learning

Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa

no code implementations6 Jul 2021 Guanxiong Shen, Junqing Zhang, Alan Marshall, Joseph Cavallaro

Radio frequency fingerprint identification (RFFI) is a promising device authentication technique based on the transmitter hardware impairments.

Data Augmentation Metric Learning

Radio Frequency Fingerprint Identification for LoRa Using Spectrogram and CNN

no code implementations30 Dec 2020 Guanxiong Shen, Junqing Zhang, Alan Marshall, Linning Peng, Xianbin Wang

Radio frequency fingerprint identification (RFFI) is an emerging device authentication technique that relies on intrinsic hardware characteristics of wireless devices.

Cannot find the paper you are looking for? You can Submit a new open access paper.