Ling Yi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ling Yi has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Jinliang Ding
Northeastern University
8 shared publications - Zhaolong Ning
School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China
8 shared publications - Amr Tolba
King Saud University
7 shared publications - Xiaojie Wang
School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China
6 shared publications - Li Zhou
College of Electronic Science and Technology, National University of Defense Technology, Changsha, China
4 shared publications - Yihang Huang
Chongqing University of Posts and Telecommunications
4 shared publications
Latest Publications
- Open Access
- 1 October 2026
- Published by KEAI Publishing in Digital Communications and Networks
- Vol. 12  (10) , 1549-1562
Protocol state machine-based vulnerability discovery in 5G core control plane: an automated fuzzing approach
- 1 October 2026
- Published by KEAI Publishing in Digital Communications and Networks
- Vol. 12  (10) , 1549-1562
Open AccessProtocol state machine-based vulnerability discovery in 5G core control plane: an automated fuzzing approach
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40  (3) , 113-120
ST-LLC: A Large-Scale and Lightweight Model Collaboration Framework for Spatio-Temporal Traffic Prediction
Sensor-cloud technology is a key enabler for transportation of smart cities, providing large-scale traffic data for analysis in increasingly complex traffic systems. However, spatio-temporal traffic data poses significant computational challenges, making it critical to fully exploit such data and explore cloud–edge collaborative intelligence in data-driven scenarios. To address this, we propose a spatio-temporal large-scale and lightweight model collaboration framework (ST-LLC), which distributes computational workloads across the cloud and edge to achieve accurate traffic prediction. In this framework, a lightweight graph network deployed at the edge captures short-term dynamics, while dual auto-encoders in the cloud extract long-term traffic priors. These heterogeneous features are then integrated through a cross-feed attention (CFA) mechanism, and a large language model (LLM) is designed to transfer domain knowledge and enhance adaptability. We evaluate the proposed framework on three real-world public datasets. Extensive experimental results demonstrate that ST-LLC effectively integrates cloud–edge traffic sequence features and achieves superior prediction accuracy compared with state-of-the-art methods. Finally, we discuss practical challenges such as communication latency and data security, and outline future directions.
- 3 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40  (3) , 113-120
ST-LLC: A Large-Scale and Lightweight Model Collaboration Framework for Spatio-Temporal Traffic Prediction
Sensor-cloud technology is a key enabler for transportation of smart cities, providing large-scale traffic data for analysis in increasingly complex traffic systems. However, spatio-temporal traffic data poses significant computational challenges, making it critical to fully exploit such data and explore cloud–edge collaborative intelligence in data-driven scenarios. To address this, we propose a spatio-temporal large-scale and lightweight model collaboration framework (ST-LLC), which distributes computational workloads across the cloud and edge to achieve accurate traffic prediction. In this framework, a lightweight graph network deployed at the edge captures short-term dynamics, while dual auto-encoders in the cloud extract long-term traffic priors. These heterogeneous features are then integrated through a cross-feed attention (CFA) mechanism, and a large language model (LLM) is designed to transfer domain knowledge and enhance adaptability. We evaluate the proposed framework on three real-world public datasets. Extensive experimental results demonstrate that ST-LLC effectively integrates cloud–edge traffic sequence features and achieves superior prediction accuracy compared with state-of-the-art methods. Finally, we discuss practical challenges such as communication latency and data security, and outline future directions.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 12185-12205
Blockchain-Enabled Hierarchical Multi-Agent Reinforcement Learning for Multi-Orbit Satellite Networks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 12185-12205
Blockchain-Enabled Hierarchical Multi-Agent Reinforcement Learning for Multi-Orbit Satellite Networks
- 8 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 5077-5091
Deep Resource Allocation for Spectrum-Aggregated AAV Multicast Systems: A Neural Combinatorial Optimization Approach
UAV-enabled multicast transmission is pivotal for low-altitude economy networking, but is fundamentally constrained by dynamic channel availability and fluctuations stemming from UAV mobility. Efficient integration of fragmented spectrum resources spanning multiple frequency bands for opportunistic multicast transmission not only elevates resource utilization but also broadens service scalability. Nevertheless, the fragmented spectrum exhibits strong frequency selectivity, compounded by the max-min objective inherent to multicast broadcast services (MBS) and the nonlinear channel aggregation characteristics, which collectively render the resource allocation problem an intricate max-min nonlinear combinatorial optimization problem. To tackle this challenge, this paper proposes an artificial general intelligence (AGI)-driven deep resource allocation algorithm for spectrum aggregation (SA)-enabled UAV-MBS systems, capable of accommodating diverse UE demands and flexible resources. A pointer network-based neural combinatorial optimization (NCO) solver, integrated with a self-reference reinforcement learning framework, is employed to achieve probability-driven sequential resource selection. Sensitivity analysis and stepwise decomposition are conducted to evaluate the effectiveness of the trained network, providing interpretability and deeper insights into the NCO solver. Simulation results demonstrate the proposed scheme’s superiority over baseline methods with significantly fewer explorations. Furthermore, the soft selection mechanism ensures robustness against inaccurate CQI knowledge, particularly in scenarios with overly optimistic channel conditions.
- 8 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 5077-5091
Deep Resource Allocation for Spectrum-Aggregated AAV Multicast Systems: A Neural Combinatorial Optimization Approach
UAV-enabled multicast transmission is pivotal for low-altitude economy networking, but is fundamentally constrained by dynamic channel availability and fluctuations stemming from UAV mobility. Efficient integration of fragmented spectrum resources spanning multiple frequency bands for opportunistic multicast transmission not only elevates resource utilization but also broadens service scalability. Nevertheless, the fragmented spectrum exhibits strong frequency selectivity, compounded by the max-min objective inherent to multicast broadcast services (MBS) and the nonlinear channel aggregation characteristics, which collectively render the resource allocation problem an intricate max-min nonlinear combinatorial optimization problem. To tackle this challenge, this paper proposes an artificial general intelligence (AGI)-driven deep resource allocation algorithm for spectrum aggregation (SA)-enabled UAV-MBS systems, capable of accommodating diverse UE demands and flexible resources. A pointer network-based neural combinatorial optimization (NCO) solver, integrated with a self-reference reinforcement learning framework, is employed to achieve probability-driven sequential resource selection. Sensitivity analysis and stepwise decomposition are conducted to evaluate the effectiveness of the trained network, providing interpretability and deeper insights into the NCO solver. Simulation results demonstrate the proposed scheme’s superiority over baseline methods with significantly fewer explorations. Furthermore, the soft selection mechanism ensures robustness against inaccurate CQI knowledge, particularly in scenarios with overly optimistic channel conditions.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (3) , 3676-3690
Efficient Cross-Chain Data Transmission via Satellite for Nonterrestrial Network-Assisted Internet of Things
The nonterrestrial networks (NTNs) have received significant attention in the global market for their contribution to the low-altitude economy. As a critical component, low-Earth orbit (LEO) satellite networks facilitate information exchange but also pose security risks due to their broadcast nature. To this end, this article presents a novel cross-chain data transmission framework based on satellite off-chain channels, integrating the security features of blockchain with the high-efficiency transmission capabilities of off-chain mechanisms to enhance the data delivery performance. Within this framework, we propose a multidimensional resource allocation model that incorporates key constraints, such as communication windows, orbital dynamics, and chain bandwidth limitations. A real-time window scheduling strategy is further developed to address both latency sensitivity and data priority. To facilitate efficient optimization under complex constraints, we propose the hypergeometric dynamic phase optimization (HDPO) algorithm. HDPO attains robust convergence by leveraging hypergeometric functions, enhances adaptive exploration via dynamic phase adjustment, and mitigates both local optima entrapment and parameter sensitivity through hybrid search strategies. Experimental evaluations demonstrate that the proposed on-chain/off-chain collaborative transmission scheme significantly reduces transmission delay and improves throughput compared to traditional on-chain methods. Moreover, the HDPO algorithm achieves the highest data transmission success rates under various interference levels, highlighting its superior robustness and environmental adaptability.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13  (3) , 3676-3690
Efficient Cross-Chain Data Transmission via Satellite for Nonterrestrial Network-Assisted Internet of Things
The nonterrestrial networks (NTNs) have received significant attention in the global market for their contribution to the low-altitude economy. As a critical component, low-Earth orbit (LEO) satellite networks facilitate information exchange but also pose security risks due to their broadcast nature. To this end, this article presents a novel cross-chain data transmission framework based on satellite off-chain channels, integrating the security features of blockchain with the high-efficiency transmission capabilities of off-chain mechanisms to enhance the data delivery performance. Within this framework, we propose a multidimensional resource allocation model that incorporates key constraints, such as communication windows, orbital dynamics, and chain bandwidth limitations. A real-time window scheduling strategy is further developed to address both latency sensitivity and data priority. To facilitate efficient optimization under complex constraints, we propose the hypergeometric dynamic phase optimization (HDPO) algorithm. HDPO attains robust convergence by leveraging hypergeometric functions, enhances adaptive exploration via dynamic phase adjustment, and mitigates both local optima entrapment and parameter sensitivity through hybrid search strategies. Experimental evaluations demonstrate that the proposed on-chain/off-chain collaborative transmission scheme significantly reduces transmission delay and improves throughput compared to traditional on-chain methods. Moreover, the HDPO algorithm achieves the highest data transmission success rates under various interference levels, highlighting its superior robustness and environmental adaptability.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75  (5) , 7121-7133
Defending AAVs Against Adversarial Attacks Using Diffusion Model
Unmanned Aerial Vehicles (UAVs) equipped with object detection algorithms are increasingly used to automate tasks traditionally requiring manual inspection. However, deep learning-based detection systems remain susceptible to patch-based adversarial attacks, which significantly decrease detection accuracy and introduce safety concerns. To address this challenge, we propose a novel two-stage defense framework against adversarial attacks. The first stage focuses on patch repair. We utilize the Segment Anything Model (SAM) to accurately generate masks of adversarial patches, followed by a diffusion model to reconstruct the corrupted image regions. To ensure real-time performance and support scalable deployment, the patch repair process is offloaded to edge servers and the cloud. In the second stage, we enhance detection robustness through a Spatial-Frequency Enhanced Alignment (SFEA) module designed to mitigate distortions introduced by the image restoration process. SFEA integrates a vision-based Long Short-Term Memory (LSTM) network with a Fused Fourier Convolution Mixer (FFCM) to extract and align spatial and frequency-domain features. A dual-stream switching module dynamically aligns these features across both domains, while a Convolutional Block Attention Module (CBAM) further enhances representational robustness. Experimental results on both benchmark and real-world datasets demonstrate that our framework outperforms existing defense methods in addressing patch-based adversarial attacks.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75  (5) , 7121-7133
Defending AAVs Against Adversarial Attacks Using Diffusion Model
Unmanned Aerial Vehicles (UAVs) equipped with object detection algorithms are increasingly used to automate tasks traditionally requiring manual inspection. However, deep learning-based detection systems remain susceptible to patch-based adversarial attacks, which significantly decrease detection accuracy and introduce safety concerns. To address this challenge, we propose a novel two-stage defense framework against adversarial attacks. The first stage focuses on patch repair. We utilize the Segment Anything Model (SAM) to accurately generate masks of adversarial patches, followed by a diffusion model to reconstruct the corrupted image regions. To ensure real-time performance and support scalable deployment, the patch repair process is offloaded to edge servers and the cloud. In the second stage, we enhance detection robustness through a Spatial-Frequency Enhanced Alignment (SFEA) module designed to mitigate distortions introduced by the image restoration process. SFEA integrates a vision-based Long Short-Term Memory (LSTM) network with a Fused Fourier Convolution Mixer (FFCM) to extract and align spatial and frequency-domain features. A dual-stream switching module dynamically aligns these features across both domains, while a Convolutional Block Attention Module (CBAM) further enhances representational robustness. Experimental results on both benchmark and real-world datasets demonstrate that our framework outperforms existing defense methods in addressing patch-based adversarial attacks.
- 15 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21  (11) , 9126-9136
A Double Knowledge Distillation Framework for Insulator Defect Detection
Insulator defect detection is essential for maintaining reliable power delivery systems. Recently, insulator image detection has emerged as a promising alternative to traditional manual inspections. However, existing datasets primarily focus on object detection, and current methods often suffer from limitations in accuracy and computational efficiency. To address these challenges, this article develops a specialized insulator defect segmentation dataset and a novel double knowledge distillation framework aimed at achieving superior detection performance with a lightweight model. The proposed method begins with fine-tuning a large-scale teacher model. A compact student model is then trained through the first knowledge distillation process, utilizing a distinctive contrastive learning strategy. Unlike existing methods that directly compare segmentation masks, we contrast the no-prompt output of the teacher model with the output mask generated by the student model, enhancing the granularity of knowledge transfer, with the underlying theory established and proven. In the second phase of distillation, generative adversarial networks facilitate deeper knowledge distillation, where the student model generates synthetic labels and the teacher model provides ground-truth labels, iteratively refining the student’s capabilities. Experimental results show that the proposed framework significantly reduces model size while maintaining high performance in insulator defect segmentation.
- 15 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21  (11) , 9126-9136
A Double Knowledge Distillation Framework for Insulator Defect Detection
Insulator defect detection is essential for maintaining reliable power delivery systems. Recently, insulator image detection has emerged as a promising alternative to traditional manual inspections. However, existing datasets primarily focus on object detection, and current methods often suffer from limitations in accuracy and computational efficiency. To address these challenges, this article develops a specialized insulator defect segmentation dataset and a novel double knowledge distillation framework aimed at achieving superior detection performance with a lightweight model. The proposed method begins with fine-tuning a large-scale teacher model. A compact student model is then trained through the first knowledge distillation process, utilizing a distinctive contrastive learning strategy. Unlike existing methods that directly compare segmentation masks, we contrast the no-prompt output of the teacher model with the output mask generated by the student model, enhancing the granularity of knowledge transfer, with the underlying theory established and proven. In the second phase of distillation, generative adversarial networks facilitate deeper knowledge distillation, where the student model generates synthetic labels and the teacher model provides ground-truth labels, iteratively refining the student’s capabilities. Experimental results show that the proposed framework significantly reduces model size while maintaining high performance in insulator defect segmentation.
- Open Access
- 11 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57  (12) , 1-35
A Survey on Off-chain Networks: Frameworks, Technologies, Solutions and Challenges
Off-chain networks that support transactions outside of the blockchain can handle large numbers of transactions and relieve the pressure on on-chain storage, showing great potential in mitigating scalability challenges of blockchain. However, since off-chain networks are still in the early stage of development, how to ensure off-chain data security, off-chain trust, off-chain transaction privacy and efficiency has become an important challenge. Against this background, this article provides a comprehensive review on off-chain networks. We first introduce the background, including design motivations, overview, and application scenarios. We then propose key issues related to off-chain networks. After that, we introduce off-chain technologies, including security and privacy based technologies, intelligent off-chain networking and routing technologies, off-chain edge computing technologies, and off-chain transaction scheduling technologies. Subsequently, we summarize mainstream solutions for corresponding key issues and provide learned lessons. Finally, we discuss some research challenges and open issues.
- 11 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57  (12) , 1-35
Open AccessA Survey on Off-chain Networks: Frameworks, Technologies, Solutions and Challenges
Off-chain networks that support transactions outside of the blockchain can handle large numbers of transactions and relieve the pressure on on-chain storage, showing great potential in mitigating scalability challenges of blockchain. However, since off-chain networks are still in the early stage of development, how to ensure off-chain data security, off-chain trust, off-chain transaction privacy and efficiency has become an important challenge. Against this background, this article provides a comprehensive review on off-chain networks. We first introduce the background, including design motivations, overview, and application scenarios. We then propose key issues related to off-chain networks. After that, we introduce off-chain technologies, including security and privacy based technologies, intelligent off-chain networking and routing technologies, off-chain edge computing technologies, and off-chain transaction scheduling technologies. Subsequently, we summarize mainstream solutions for corresponding key issues and provide learned lessons. Finally, we discuss some research challenges and open issues.
- 9 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71  (1) , 2039-2050
Sensitivity Analysis-Based Explainable Diffusion Transformers for Anomaly Detection in Consumer Electronics Manufacturing
Consumer electronics play a crucial role in the artificial intelligence internet of things (AIoT), with anomaly detection (AD) being particularly critical for the consumer product manufacturing industry. However, existing AD methods suffer from limitations such as poor detection accuracy and lack of explainability, hindering their widespread adoption in industrial manufacturing. To address these issues, we propose SADiTAD, a Sensitivity Analysis-based Diffusion Transformer for Anomaly Detection. This model comprises a diffusion transformer (DiT)-based reconstruction enhancement sub-network and a vision transformer (ViT)-based detection sub-network. In the DiT sub-network, we introduce a structural similarity index measure (SSIM)-guided one-step denoising method to expedite the denoising process. Additionally, to enhance the model’s explainability, we develop a sensitivity analysis-based ViT (SA-ViT) model, which evaluates the sensitivity of input embeddings to various image regions to determine if the fault region is being accurately identified during anomaly detection. The proposed SADiTAD model has been evaluated on public datasets MVTec AD and VisA, demonstrating superior performance over existing state-of-the-art anomaly detection methods and providing enhanced explainability.
- 9 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71  (1) , 2039-2050
Sensitivity Analysis-Based Explainable Diffusion Transformers for Anomaly Detection in Consumer Electronics Manufacturing
Consumer electronics play a crucial role in the artificial intelligence internet of things (AIoT), with anomaly detection (AD) being particularly critical for the consumer product manufacturing industry. However, existing AD methods suffer from limitations such as poor detection accuracy and lack of explainability, hindering their widespread adoption in industrial manufacturing. To address these issues, we propose SADiTAD, a Sensitivity Analysis-based Diffusion Transformer for Anomaly Detection. This model comprises a diffusion transformer (DiT)-based reconstruction enhancement sub-network and a vision transformer (ViT)-based detection sub-network. In the DiT sub-network, we introduce a structural similarity index measure (SSIM)-guided one-step denoising method to expedite the denoising process. Additionally, to enhance the model’s explainability, we develop a sensitivity analysis-based ViT (SA-ViT) model, which evaluates the sensitivity of input embeddings to various image regions to determine if the fault region is being accurately identified during anomaly detection. The proposed SADiTAD model has been evaluated on public datasets MVTec AD and VisA, demonstrating superior performance over existing state-of-the-art anomaly detection methods and providing enhanced explainability.