Yufan Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yufan Chen has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Lei Zhu
Army Engineering University of PLA
8 shared publications - Yuantao Gu
Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China
6 shared publications Lu Yu
4 shared publications- Wenyu Wang
Army Engineering University of PLA
4 shared publications - Changhua Yao
School Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, China
3 shared publications - Kaixin Cheng
Army Engineering University of PLA
3 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 72 (4) , 12643-12654
UAV Relay Selection and Resource Scheduling System Based on Hierarchical Graph Attention Reinforcement Learning
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 72 (4) , 12643-12654
UAV Relay Selection and Resource Scheduling System Based on Hierarchical Graph Attention Reinforcement Learning
- Open Access
- 1 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 705
DMBS: A band-limited Gaussian noise cancellation algorithm based on a diffusion model and Bhattacharyya step-number guidance
- 1 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 705
Open AccessDMBS: A band-limited Gaussian noise cancellation algorithm based on a diffusion model and Bhattacharyya step-number guidance
- Top Cited Papers
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2769-2784
Enhancing Data Augmentation Diversity: A Diffusion Model-Based Approach for Few-Shot Specific Emitter Identification
Specific emitter identification (SEI) separates the radio frequency fingerprint (RFF) from signals, which is of great significance in solving Internet of Things (IoT) security problems. However, the scarcity of high-quality, diverse, and labeled data in real-world scenarios limits the application of SEI. Under such conditions, the SEI is referred to as few-shot SEI (FS-SEI). To surmount this challenge, we propose a diffusion model-based data augmentation method capable of generating a substantial volume of diverse, high-quality data. Specifically, we develop a multi-scale convolutional block attention module denoising diffusion probabilistic model (MSCBAM-DDPM), which enhances feature capture capabilities, laying the foundation for the generation of diverse data. Furthermore, we propose an adaptive two-stage multi-domain loss function that guides the model to learn the characteristics of the original data and further derive other similar features, thereby achieving the goal of generating diverse and high-quality data. Finally, we theoretically derive the feasibility of the proposed loss function and further demonstrate the excellent diversity and quality of the data generated by our method, as well as its considerable gain for FS-SEI, through extensive experiments on real-world signal datasets.
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2769-2784
Top Cited PapersEnhancing Data Augmentation Diversity: A Diffusion Model-Based Approach for Few-Shot Specific Emitter Identification
Specific emitter identification (SEI) separates the radio frequency fingerprint (RFF) from signals, which is of great significance in solving Internet of Things (IoT) security problems. However, the scarcity of high-quality, diverse, and labeled data in real-world scenarios limits the application of SEI. Under such conditions, the SEI is referred to as few-shot SEI (FS-SEI). To surmount this challenge, we propose a diffusion model-based data augmentation method capable of generating a substantial volume of diverse, high-quality data. Specifically, we develop a multi-scale convolutional block attention module denoising diffusion probabilistic model (MSCBAM-DDPM), which enhances feature capture capabilities, laying the foundation for the generation of diverse data. Furthermore, we propose an adaptive two-stage multi-domain loss function that guides the model to learn the characteristics of the original data and further derive other similar features, thereby achieving the goal of generating diverse and high-quality data. Finally, we theoretically derive the feasibility of the proposed loss function and further demonstrate the excellent diversity and quality of the data generated by our method, as well as its considerable gain for FS-SEI, through extensive experiments on real-world signal datasets.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 1543-1547
Boundary-Aware Margin Shaping for Joint Open-Set Modulation Recognition and Adversarial Robustness
Robust automatic modulation recognition (AMR) under open-set conditions and adversarial attacks remains a critical challenge for secure and reliable wireless communication. This letter proposes a Boundary-aware Margin Shaping (BMS) framework that unifies open-set recognition and adversarial robustness through adaptive boundary modeling. BMS introduces a margin-aware training scheme that jointly stabilizes feature representations, calibrates confidence, and smooths decision boundaries under adversarial conditions. For inference, we employ a standard KNN detector to perform out-of-distribution (OOD) separation. Comprehensive experiments on the RML2016.10a dataset demonstrate that BMS consistently achieves superior classification and OOD detection performance across various SNRs and adversarial attacks.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 1543-1547
Boundary-Aware Margin Shaping for Joint Open-Set Modulation Recognition and Adversarial Robustness
Robust automatic modulation recognition (AMR) under open-set conditions and adversarial attacks remains a critical challenge for secure and reliable wireless communication. This letter proposes a Boundary-aware Margin Shaping (BMS) framework that unifies open-set recognition and adversarial robustness through adaptive boundary modeling. BMS introduces a margin-aware training scheme that jointly stabilizes feature representations, calibrates confidence, and smooths decision boundaries under adversarial conditions. For inference, we employ a standard KNN detector to perform out-of-distribution (OOD) separation. Comprehensive experiments on the RML2016.10a dataset demonstrate that BMS consistently achieves superior classification and OOD detection performance across various SNRs and adversarial attacks.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 3753-3769
Joint Deployment, Power Control, and Beamforming Designs for Movable Antenna-Aided UAV Communication: A DRL-Based Two-Stage Approach
Movable antenna (MA) technology enables flexible beamforming through adaptive adjustment of antenna positions, thereby enhancing communication performance. This paper investigates the MA-aided air-to-ground (A2G) system, where an unmanned aerial vehicle (UAV) equipped with MAs serves multiple ground users. The primary objective is to jointly optimize UAV deployment, antenna positions, beamforming, and power control to maximize the downlink communication sum rate. A key challenge lies in the difficulty of acquiring complete instantaneous channel state information (I-CSI), as the antennas cannot traverse all possible positions to obtain such full-scale I-CSI, which impedes the efficient optimization of system parameters. To address this challenge, we propose a two-stage transmission scheme: in the first stage, location-aware statistical CSI (S-CSI) is leveraged to optimize UAV deployment, power control, and MA positions for maximizing long-term system performance, while the second stage estimates I-CSI based on the optimized UAV and antenna positions to refine short-term transmit beamforming after long-term variables are determined, thereby substantially reducing CSI acquisition overhead. For long-term policy optimization, we introduce a novel dual-spatial-scale hierarchical deep reinforcement learning (DSSH-DRL) framework, which preserves flexibility in global policy formulation while enhancing training efficiency via effective decoupling of control variables. Simulation results demonstrate the effectiveness of the proposed algorithm and validate the promising application potential of MA technology in A2G communication networks.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 3753-3769
Joint Deployment, Power Control, and Beamforming Designs for Movable Antenna-Aided UAV Communication: A DRL-Based Two-Stage Approach
Movable antenna (MA) technology enables flexible beamforming through adaptive adjustment of antenna positions, thereby enhancing communication performance. This paper investigates the MA-aided air-to-ground (A2G) system, where an unmanned aerial vehicle (UAV) equipped with MAs serves multiple ground users. The primary objective is to jointly optimize UAV deployment, antenna positions, beamforming, and power control to maximize the downlink communication sum rate. A key challenge lies in the difficulty of acquiring complete instantaneous channel state information (I-CSI), as the antennas cannot traverse all possible positions to obtain such full-scale I-CSI, which impedes the efficient optimization of system parameters. To address this challenge, we propose a two-stage transmission scheme: in the first stage, location-aware statistical CSI (S-CSI) is leveraged to optimize UAV deployment, power control, and MA positions for maximizing long-term system performance, while the second stage estimates I-CSI based on the optimized UAV and antenna positions to refine short-term transmit beamforming after long-term variables are determined, thereby substantially reducing CSI acquisition overhead. For long-term policy optimization, we introduce a novel dual-spatial-scale hierarchical deep reinforcement learning (DSSH-DRL) framework, which preserves flexibility in global policy formulation while enhancing training efficiency via effective decoupling of control variables. Simulation results demonstrate the effectiveness of the proposed algorithm and validate the promising application potential of MA technology in A2G communication networks.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 4640-4655
S3AT: Self-Paced, Self-Distilled, and Self-Finetuned Adversarial Training for Robust Automatic Modulation Recognition
Deep learning-based automatic modulation recognition (AMR) models are highly susceptible to adversarial samples. Although adversarial training offers a promising defense, most existing methods rely on fixed-intensity attacks and lack mechanisms to maintain stable feature representations, limiting recognition performance under diverse adversarial conditions. To address these issues, we propose S3AT, an adversarial training framework that integrates Self-paced learning, Self-distillation, and Self-finetuning. In the self-paced phase, a progressive, difficulty-aware training paradigm adaptively schedules adversarial strength to help the model gradually adapt from weak to strong attacks. An exponential moving average (EMA) teacher provides continuous self-distillation throughout training to stabilize feature learning and mitigate forgetting of early knowledge. In the self-finetuning phase, historical checkpoints serve as auxiliary teachers, complementing the self-distillation and enhancing robustness across varying intensities of adversarial attacks. Experiments on public and self-collected datasets confirm that S3AT outperforms baseline methods under both white-box and black-box attacks. Its compatibility with external defenses further highlights its flexibility for real-world electromagnetic applications. Code is available at https://gitee.com/wwenyuu/s3-at.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 4640-4655
S3AT: Self-Paced, Self-Distilled, and Self-Finetuned Adversarial Training for Robust Automatic Modulation Recognition
Deep learning-based automatic modulation recognition (AMR) models are highly susceptible to adversarial samples. Although adversarial training offers a promising defense, most existing methods rely on fixed-intensity attacks and lack mechanisms to maintain stable feature representations, limiting recognition performance under diverse adversarial conditions. To address these issues, we propose S3AT, an adversarial training framework that integrates Self-paced learning, Self-distillation, and Self-finetuning. In the self-paced phase, a progressive, difficulty-aware training paradigm adaptively schedules adversarial strength to help the model gradually adapt from weak to strong attacks. An exponential moving average (EMA) teacher provides continuous self-distillation throughout training to stabilize feature learning and mitigate forgetting of early knowledge. In the self-finetuning phase, historical checkpoints serve as auxiliary teachers, complementing the self-distillation and enhancing robustness across varying intensities of adversarial attacks. Experiments on public and self-collected datasets confirm that S3AT outperforms baseline methods under both white-box and black-box attacks. Its compatibility with external defenses further highlights its flexibility for real-world electromagnetic applications. Code is available at https://gitee.com/wwenyuu/s3-at.
- 14 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 11 (5) , 2893-2909
STAR-RIS-Empowered Integrated Sensing and Covert Communication System With Movable Elements: Joint Robust Beamforming and Element Deployment Design
This paper investigates the integrated sensing and covert communication (ISCC) system, which is empowered by a simultaneous transmission and reflection reconfigurable intelligent surface (STAR-RIS) with movable elements (MEs). The base station (BS) serves legitimate users (including covert inside users and overt outside users) with the assistance of a STARRIS and senses several malicious targets simultaneously. To protect the information of covert users, it is necessary to ensure that the communications between the BS and covert users are hidden from the sensing targets. The STAR-RIS is equipped with MEs that enable a reconfigurable array response and signal control (reflection/transmission), i.e., flexible and passive beamforming (FAPB). Based on the imperfect channel state information (CSI) assumption, we aim to maximize both the communication and the sensing performance by jointly designing the active beamforming of BS and the FAPB of STAR-RIS. Both STAR-RISs with independent and coupled phase shift are considered. For the case of independent phase shift, we develop an iteration-based joint active and flexible passive beamforming (JAFPB) algorithm to obtain a high-quality solution. For the case of coupled phase shift, we develop a double-layer penalty-based iteration (DLPBI) algorithm to efficiently solve this problem. The numerical results validate the effectiveness and robustness of the proposed algorithm and further reveal that element mobility can improve the performance of the STAR-RIS-aided system.
- 14 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 11 (5) , 2893-2909
STAR-RIS-Empowered Integrated Sensing and Covert Communication System With Movable Elements: Joint Robust Beamforming and Element Deployment Design
This paper investigates the integrated sensing and covert communication (ISCC) system, which is empowered by a simultaneous transmission and reflection reconfigurable intelligent surface (STAR-RIS) with movable elements (MEs). The base station (BS) serves legitimate users (including covert inside users and overt outside users) with the assistance of a STARRIS and senses several malicious targets simultaneously. To protect the information of covert users, it is necessary to ensure that the communications between the BS and covert users are hidden from the sensing targets. The STAR-RIS is equipped with MEs that enable a reconfigurable array response and signal control (reflection/transmission), i.e., flexible and passive beamforming (FAPB). Based on the imperfect channel state information (CSI) assumption, we aim to maximize both the communication and the sensing performance by jointly designing the active beamforming of BS and the FAPB of STAR-RIS. Both STAR-RISs with independent and coupled phase shift are considered. For the case of independent phase shift, we develop an iteration-based joint active and flexible passive beamforming (JAFPB) algorithm to obtain a high-quality solution. For the case of coupled phase shift, we develop a double-layer penalty-based iteration (DLPBI) algorithm to efficiently solve this problem. The numerical results validate the effectiveness and robustness of the proposed algorithm and further reveal that element mobility can improve the performance of the STAR-RIS-aided system.
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (1) , 1
Prototype-Driven Unsupervised Domain Adaptation for Specific Emitter Identification
Distribution shift is a prominent challenge for specific emitter identification (SEI) in non-cooperative scenarios. Unsupervised domain adaptation (UDA) aims to address the aforementioned issue by transferring knowledge from labeled source domain to unlabeled target domain. However, existing UDA methods primarily focus on cross-domain alignment of global features, causing less discriminability between features of different classes. Building upon this observation, we leverage prototypes to extract domain-invariant class knowledge and propose a Prototype-Driven Unsupervised Domain Adaptation (PDDA) framework to enhance the discriminability of different classes. Firstly, we propose a pseudo-label mechanism to assist the target domain in self-supervised training, utilizing unlabeled samples to learn discriminative feature. Secondly, building upon the relationship between features and the corresponding prototypes, we propose a prototypical bidirectional alignment (PBA) method to achieve class-level transfer. Finally, we propose a prediction consistency constraint to balance transferability and discriminability of features. The proposed method is compared with state-of-the-art methods on two publicly available radio frequency fingerprint datasets and the results demonstrate the effectiveness of PDDA.
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (1) , 1
Prototype-Driven Unsupervised Domain Adaptation for Specific Emitter Identification
Distribution shift is a prominent challenge for specific emitter identification (SEI) in non-cooperative scenarios. Unsupervised domain adaptation (UDA) aims to address the aforementioned issue by transferring knowledge from labeled source domain to unlabeled target domain. However, existing UDA methods primarily focus on cross-domain alignment of global features, causing less discriminability between features of different classes. Building upon this observation, we leverage prototypes to extract domain-invariant class knowledge and propose a Prototype-Driven Unsupervised Domain Adaptation (PDDA) framework to enhance the discriminability of different classes. Firstly, we propose a pseudo-label mechanism to assist the target domain in self-supervised training, utilizing unlabeled samples to learn discriminative feature. Secondly, building upon the relationship between features and the corresponding prototypes, we propose a prototypical bidirectional alignment (PBA) method to achieve class-level transfer. Finally, we propose a prediction consistency constraint to balance transferability and discriminability of features. The proposed method is compared with state-of-the-art methods on two publicly available radio frequency fingerprint datasets and the results demonstrate the effectiveness of PDDA.
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (11) , 2483-2487
Adversarial Samples Detection Based on Feature Attribution and Contrast in Modulation Recognition
Detecting adversarial samples is crucial for maintaining the security of automatic modulation recognition (AMR) systems, as adversarial attacks could severely compromise wireless communication. To address this threat, we propose a novel adversarial samples detection method named Null Feature Attribution Abnormality (NFAA), which leverages the target model’s interpretation of feature importance to distinguish between benign and adversarial signal samples. Furthermore, we propose the NFAA-TC method, incorporating a Triple Contrast (TC) approach to mitigate noise in signal data and enhance the performance of adversarial samples detection. Experimental results validate the effectiveness of the proposed method across various adversarial attacks and under different signal-to-noise ratio (SNR) conditions.
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (11) , 2483-2487
Adversarial Samples Detection Based on Feature Attribution and Contrast in Modulation Recognition
Detecting adversarial samples is crucial for maintaining the security of automatic modulation recognition (AMR) systems, as adversarial attacks could severely compromise wireless communication. To address this threat, we propose a novel adversarial samples detection method named Null Feature Attribution Abnormality (NFAA), which leverages the target model’s interpretation of feature importance to distinguish between benign and adversarial signal samples. Furthermore, we propose the NFAA-TC method, incorporating a Triple Contrast (TC) approach to mitigate noise in signal data and enhance the performance of adversarial samples detection. Experimental results validate the effectiveness of the proposed method across various adversarial attacks and under different signal-to-noise ratio (SNR) conditions.
- 6 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 13 (7) , 1958-1962
Counterfactual Threshold Learning for Drone RF Signal Classification Under Interference Conditions
Drones utilize radio frequency (RF) signals for communication, providing pertinent information about their activities. The RF-based drone wireless monitoring system is expected to effectively achieve precise identification of types and operational modes in real-world scenarios, thereby providing more valuable information for drone regulation. The realization of the these objectives primarily confronts two challenges: mitigating the impact of noise and interference on feature learning and simultaneously accomplishing coarse-grained and fine-grained classification tasks of RF signals. Building upon the aforementioned considerations, we propose a neural collapse (NC)-inspired Counterfactual Threshold Learning (CTL) framework. The proposed framework leverages counterfactual causality to guide the neural network (NN) in accurate threshold learning, thereby more effectively eliminating noise-related features. Meanwhile, based on the NC, we keep the classifier’s simplex Equiangular Tight Frame (ETF) structure unchanged during training and solely train the intermediate layers. This strategy guarantees consistent class prototypes, preventing performance degradation caused by the proximity of prototypes in fine-grained tasks. We integrate the aforementioned techniques into CTL framework and thoroughly validate it using two open-source datasets.
- 6 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 13 (7) , 1958-1962
Counterfactual Threshold Learning for Drone RF Signal Classification Under Interference Conditions
Drones utilize radio frequency (RF) signals for communication, providing pertinent information about their activities. The RF-based drone wireless monitoring system is expected to effectively achieve precise identification of types and operational modes in real-world scenarios, thereby providing more valuable information for drone regulation. The realization of the these objectives primarily confronts two challenges: mitigating the impact of noise and interference on feature learning and simultaneously accomplishing coarse-grained and fine-grained classification tasks of RF signals. Building upon the aforementioned considerations, we propose a neural collapse (NC)-inspired Counterfactual Threshold Learning (CTL) framework. The proposed framework leverages counterfactual causality to guide the neural network (NN) in accurate threshold learning, thereby more effectively eliminating noise-related features. Meanwhile, based on the NC, we keep the classifier’s simplex Equiangular Tight Frame (ETF) structure unchanged during training and solely train the intermediate layers. This strategy guarantees consistent class prototypes, preventing performance degradation caused by the proximity of prototypes in fine-grained tasks. We integrate the aforementioned techniques into CTL framework and thoroughly validate it using two open-source datasets.