Zhenxin Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhenxin Cai has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Guan Gui
Nanjing University of Posts and Telecommunications
5 shared publications - Yun Lin
Harbin Engineering University
3 shared publications - Jin Sha
Nanjing University
2 shared publications - Qin Wang
Nanjing University of Posts and Telecommunications
2 shared publications - Rui Wang
College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China
2 shared publications Siqi Lou
Hebei university of Technology
2 shared publications
Latest Publications
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2641-2651
Toward Robust Radio Frequency Fingerprint Identification: A Federated Learning Framework With Feature Alignment
With the growing adoption of Internet of Things (IoT) devices, ensuring the security of wireless communications has become increasingly critical. Radio frequency fingerprint identification (RFFI) has shown promise in this regard due to its capability of uniquely identifying devices. Although deep learning (DL) approaches have significantly improved RFFI performance, they typically rely on large-scale centralized data. This poses challenges in terms of privacy preservation and heterogeneous data distributions. To address the performance degradation caused by non-independent and identically distributed (non-IID) data in cross-receiver scenarios, this paper proposes a feature alignment strategy based on federated learning (FL) for RFFI. In such scenarios, due to differences in receiver hardware characteristics, deployment locations, and channel conditions, the signals captured by different receivers often exhibit distribution shifts, resulting in misaligned feature spaces across clients. The proposed method guides each client to learn aligned intermediate feature representations during local training, effectively mitigating the resulting adverse impact on model generalization. Experiments conducted on a real-world RF dataset demonstrate that the proposed method achieves higher identification accuracy and improved stability compared with representative federated baselines, including FedAvg and FedProx. The highest identification accuracy reaches 90.83%, and the performance gains are accompanied by generally reduced variance across different client configurations, highlighting the robustness and generalization capability of the proposed approach in heterogeneous wireless environments.
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2641-2651
Toward Robust Radio Frequency Fingerprint Identification: A Federated Learning Framework With Feature Alignment
With the growing adoption of Internet of Things (IoT) devices, ensuring the security of wireless communications has become increasingly critical. Radio frequency fingerprint identification (RFFI) has shown promise in this regard due to its capability of uniquely identifying devices. Although deep learning (DL) approaches have significantly improved RFFI performance, they typically rely on large-scale centralized data. This poses challenges in terms of privacy preservation and heterogeneous data distributions. To address the performance degradation caused by non-independent and identically distributed (non-IID) data in cross-receiver scenarios, this paper proposes a feature alignment strategy based on federated learning (FL) for RFFI. In such scenarios, due to differences in receiver hardware characteristics, deployment locations, and channel conditions, the signals captured by different receivers often exhibit distribution shifts, resulting in misaligned feature spaces across clients. The proposed method guides each client to learn aligned intermediate feature representations during local training, effectively mitigating the resulting adverse impact on model generalization. Experiments conducted on a real-world RF dataset demonstrate that the proposed method achieves higher identification accuracy and improved stability compared with representative federated baselines, including FedAvg and FedProx. The highest identification accuracy reaches 90.83%, and the performance gains are accompanied by generally reduced variance across different client configurations, highlighting the robustness and generalization capability of the proposed approach in heterogeneous wireless environments.
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 22183-22193
Bridging Modulation Gaps: Similarity-Aware Domain-Invariant Learning for Robust Radio Frequency Fingerprint Identification
Radio frequency fingerprint identification (RFFI) has emerged as a promising technique for enhancing wireless security by uniquely identifying individual devices through their inherent RF characteristics. However, the performance of conventional RFFI methods deteriorates significantly when training and testing involve different modulation schemes, primarily due to the resulting domain shift between modulation types. To address this challenge, this article proposes domain-invariant adaptive mixup enhancement (DIAME), a novel framework that integrates domain-invariant feature extraction with a similarity-aware adaptive mixup strategy to improve generalization across modulation domains. Specifically, DIAME dynamically adjusts the mixup intensity based on interfeature similarity and incorporates domain alignment and feature matching with pretrained models to promote modulation-invariant representation learning. Extensive experiments on a synthetic RF dataset comprising four modulation types and five devices demonstrate that DIAME achieves an average cross-modulation identification accuracy of 86.18%, significantly outperforming state-of-the-art methods. These results confirm the effectiveness of DIAME in mitigating domain shift and highlight its suitability for robust RFFI in heterogeneous wireless communication environments.
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 22183-22193
Bridging Modulation Gaps: Similarity-Aware Domain-Invariant Learning for Robust Radio Frequency Fingerprint Identification
Radio frequency fingerprint identification (RFFI) has emerged as a promising technique for enhancing wireless security by uniquely identifying individual devices through their inherent RF characteristics. However, the performance of conventional RFFI methods deteriorates significantly when training and testing involve different modulation schemes, primarily due to the resulting domain shift between modulation types. To address this challenge, this article proposes domain-invariant adaptive mixup enhancement (DIAME), a novel framework that integrates domain-invariant feature extraction with a similarity-aware adaptive mixup strategy to improve generalization across modulation domains. Specifically, DIAME dynamically adjusts the mixup intensity based on interfeature similarity and incorporates domain alignment and feature matching with pretrained models to promote modulation-invariant representation learning. Extensive experiments on a synthetic RF dataset comprising four modulation types and five devices demonstrate that DIAME achieves an average cross-modulation identification accuracy of 86.18%, significantly outperforming state-of-the-art methods. These results confirm the effectiveness of DIAME in mitigating domain shift and highlight its suitability for robust RFFI in heterogeneous wireless communication environments.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4533-4537
Wavelet-Guided Frequency Decoupling for Channel-Robust UAV RFFI
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4533-4537
Wavelet-Guided Frequency Decoupling for Channel-Robust UAV RFFI
- 12 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 29 (10) , 2396-2400
Receiver-Agnostic Radio Frequency Fingerprinting via Domain-Invariant Feature Learning
Radio Frequency Fingerprinting (RFF) is an emerging physical-layer authentication technique that leverages intrinsic hardware imperfections introduced during the manufacturing of IoT devices. These device-specific features, inherently embedded in emitted RF signals, enable passive and non-intrusive device identification. While most existing RFF methods rely on data from a single receiver, real-world IoT deployments typically involve heterogeneous receivers, leading to cross-receiver domain shifts that severely degrade identification performance. However, research addressing this issue remains limited. To address this challenge, we propose a receiver-agnostic RFF framework that enhances generalization by learning domain-invariant features through a dual-perspective feature extraction strategy. Specifically, Fourier phase information is leveraged for its semantic stability and robustness to domain shifts. A knowledge distillation framework is introduced to extract intra-domain invariant features from the phase component, ensuring feature consistency within each receiver. In addition, a cross-domain correlation alignment mechanism is employed to capture shared representations across receivers, thereby improving robustness to distributional variations. Extensive experiments demonstrate that the proposed method consistently outperforms state-of-the-art domain generalization techniques. Moreover, results show that increasing the number of training receivers significantly improves identification accuracy in unseen receiver scenarios. The codes can be downloaded from https://github.com/Edith-xx/Receiver-agnostic-RFFI-CL-.
- 12 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 29 (10) , 2396-2400
Receiver-Agnostic Radio Frequency Fingerprinting via Domain-Invariant Feature Learning
Radio Frequency Fingerprinting (RFF) is an emerging physical-layer authentication technique that leverages intrinsic hardware imperfections introduced during the manufacturing of IoT devices. These device-specific features, inherently embedded in emitted RF signals, enable passive and non-intrusive device identification. While most existing RFF methods rely on data from a single receiver, real-world IoT deployments typically involve heterogeneous receivers, leading to cross-receiver domain shifts that severely degrade identification performance. However, research addressing this issue remains limited. To address this challenge, we propose a receiver-agnostic RFF framework that enhances generalization by learning domain-invariant features through a dual-perspective feature extraction strategy. Specifically, Fourier phase information is leveraged for its semantic stability and robustness to domain shifts. A knowledge distillation framework is introduced to extract intra-domain invariant features from the phase component, ensuring feature consistency within each receiver. In addition, a cross-domain correlation alignment mechanism is employed to capture shared representations across receivers, thereby improving robustness to distributional variations. Extensive experiments demonstrate that the proposed method consistently outperforms state-of-the-art domain generalization techniques. Moreover, results show that increasing the number of training receivers significantly improves identification accuracy in unseen receiver scenarios. The codes can be downloaded from https://github.com/Edith-xx/Receiver-agnostic-RFFI-CL-.
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (20) , 42728-42740
Lightweight and Efficient Hybrid Network for UAV Identification Using Radio Frequency Fingerprinting
The widespread use of unmanned aerial vehicles brings both convenience and potential security risks, posing significant challenges for accurate UAV identification. To address the limitations of existing deep learning-based radio frequency fingerprinting methods in terms of computational complexity and model adaptability, this paper proposes an innovative hybrid model that combines Convolutional Neural Networks and Transformers to exploit both local and global features of RF signals fully. Our model consists of a Local Block and a Global Block. The Local Block employs Partial Convolution for feature extraction, PointWise Convolution to enhance feature representation, and the Squeeze-and-Excitation module to adaptively emphasize critical features, thereby improving local feature expressiveness. The Global Block comprises Unfold, Super Token Transformer Block, and Fold, which together enable effective modeling of global dependencies through signal unfolding, spatiotemporal transformations, and reconstruction. Experimental results show that under signal-to-noise ratio (SNR) conditions ranging from –5 dB to 20 dB, our method achieves an average recognition accuracy of 96.89%, with powerful performance under low SNR conditions. Furthermore, experiments demonstrate the model’s robustness with limited data. Even with only 1,000 training samples, the model maintains an accuracy of 92.14%. When incorporating Mixup data augmentation, high classification performance is sustained with just 500 training samples. These results highlight the method’s strong adaptability and practical potential in complex environments. Our codes and models are available at https://github.com/Zhoukaijie-hy/hybrid-model.
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (20) , 42728-42740
Lightweight and Efficient Hybrid Network for UAV Identification Using Radio Frequency Fingerprinting
The widespread use of unmanned aerial vehicles brings both convenience and potential security risks, posing significant challenges for accurate UAV identification. To address the limitations of existing deep learning-based radio frequency fingerprinting methods in terms of computational complexity and model adaptability, this paper proposes an innovative hybrid model that combines Convolutional Neural Networks and Transformers to exploit both local and global features of RF signals fully. Our model consists of a Local Block and a Global Block. The Local Block employs Partial Convolution for feature extraction, PointWise Convolution to enhance feature representation, and the Squeeze-and-Excitation module to adaptively emphasize critical features, thereby improving local feature expressiveness. The Global Block comprises Unfold, Super Token Transformer Block, and Fold, which together enable effective modeling of global dependencies through signal unfolding, spatiotemporal transformations, and reconstruction. Experimental results show that under signal-to-noise ratio (SNR) conditions ranging from –5 dB to 20 dB, our method achieves an average recognition accuracy of 96.89%, with powerful performance under low SNR conditions. Furthermore, experiments demonstrate the model’s robustness with limited data. Even with only 1,000 training samples, the model maintains an accuracy of 92.14%. When incorporating Mixup data augmentation, high classification performance is sustained with just 500 training samples. These results highlight the method’s strong adaptability and practical potential in complex environments. Our codes and models are available at https://github.com/Zhoukaijie-hy/hybrid-model.