Borui Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Borui Li has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Xiaolei Zhou
National University of Defense Technology
3 shared publications - Zhao-Dong Xu
Southeast University
2 shared publications - Bowen Jiang
College of Computer Science The State Key Laboratory of Blockchain and Data Security Zhejiang University China
1 shared publication - Chongyang Song
Southeast University
1 shared publication Hailong Lin
College of Computer Science The State Key Laboratory of Blockchain and Data Security Zhejiang University China
1 shared publication- Luoyu Mei
Southeast University
1 shared publication
Latest Publications
- Open Access
- 16 January 2026
- Published by Springer Nature in CCF Transactions on Pervasive Computing and Interaction
- Vol. 8 (1) , 116-129
Synthesizing mmWave range-doppler data from videos for privacy-preserving human activity recognition
Millimeter-wave radar has shown significant potential in privacy-preserving human activity recognition. However, the lack of diverse radar datasets across various scenarios poses a challenge to the robustness and generalization of deep learning models. To address this limitation, existing works mainly focus on synthesizing micro-doppler data from video, range-doppler data, which provides an extra dimension, has been overlooked due to challenges caused by signal offsets. In this paper, we propose a comprehensive approach for synthesizing range-doppler data from videos by leveraging computer vision techniques and principles of camera imaging. Furthermore, we implement a map enhancement and classification model to facilitate human activity recognition. Our approach is validated on a custom dataset, where the proposed range-doppler synthesis method and classification model achieve an accuracy of 97.3% for activity recognition tasks. This performance is comparable to that of vision-based HAR methods, demonstrating the effectiveness of our proposed scheme in achieving privacy-preserving human activity recognition.
- 16 January 2026
- Published by Springer Nature in CCF Transactions on Pervasive Computing and Interaction
- Vol. 8 (1) , 116-129
Open AccessSynthesizing mmWave range-doppler data from videos for privacy-preserving human activity recognition
Millimeter-wave radar has shown significant potential in privacy-preserving human activity recognition. However, the lack of diverse radar datasets across various scenarios poses a challenge to the robustness and generalization of deep learning models. To address this limitation, existing works mainly focus on synthesizing micro-doppler data from video, range-doppler data, which provides an extra dimension, has been overlooked due to challenges caused by signal offsets. In this paper, we propose a comprehensive approach for synthesizing range-doppler data from videos by leveraging computer vision techniques and principles of camera imaging. Furthermore, we implement a map enhancement and classification model to facilitate human activity recognition. Our approach is validated on a custom dataset, where the proposed range-doppler synthesis method and classification model achieve an accuracy of 97.3% for activity recognition tasks. This performance is comparable to that of vision-based HAR methods, demonstrating the effectiveness of our proposed scheme in achieving privacy-preserving human activity recognition.
- Open Access
TensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE
To safeguard user data privacy, on-device inference has emerged as a prominent paradigm on mobile and Internet of Things (IoT) devices. This paradigm involves deploying a model provided by a third party on local devices to perform inference tasks. However, it exposes the private model to two primary security threats: model stealing (MS) and membership inference attacks (MIA). To mitigate these risks, existing wisdom deploys models within Trusted Execution Environments (TEEs), which is a secure isolated execution space. Nonetheless, the constrained secure memory capacity in TEEs makes it challenging to achieve full model security with low inference latency. This paper fills the gap with TensorShield, the first efficient on-device inference work that shields partial tensors of the model while still fully defending against MS and MIA. The key enabling techniques in TensorShield include: (i) a novel eXplainable AI (XAI) technique exploits the model's attention transition to assess critical tensors and shields them in TEE to achieve secure inference, and (ii) two meticulous designs with critical feature identification and latency-aware placement to accelerate inference while maintaining security. Extensive evaluations show that TensorShield delivers almost the same security protection as shielding the entire model inside TEE, while being up to 25.35$\times$ (avg. 5.85$\times$) faster than the state-of-the-art work, without accuracy loss.
Open AccessTensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE
To safeguard user data privacy, on-device inference has emerged as a prominent paradigm on mobile and Internet of Things (IoT) devices. This paradigm involves deploying a model provided by a third party on local devices to perform inference tasks. However, it exposes the private model to two primary security threats: model stealing (MS) and membership inference attacks (MIA). To mitigate these risks, existing wisdom deploys models within Trusted Execution Environments (TEEs), which is a secure isolated execution space. Nonetheless, the constrained secure memory capacity in TEEs makes it challenging to achieve full model security with low inference latency. This paper fills the gap with TensorShield, the first efficient on-device inference work that shields partial tensors of the model while still fully defending against MS and MIA. The key enabling techniques in TensorShield include: (i) a novel eXplainable AI (XAI) technique exploits the model's attention transition to assess critical tensors and shields them in TEE to achieve secure inference, and (ii) two meticulous designs with critical feature identification and latency-aware placement to accelerate inference while maintaining security. Extensive evaluations show that TensorShield delivers almost the same security protection as shielding the entire model inside TEE, while being up to 25.35$\times$ (avg. 5.85$\times$) faster than the state-of-the-art work, without accuracy loss.
- 1 March 2025
- Published by Springer Nature
- p. 118-129
EdgeMeter: Towards Efficient and Accurate Latency Prediction of Neural Network Model Inference on Edge Devices
- 1 March 2025
- Published by Springer Nature
- p. 118-129
EdgeMeter: Towards Efficient and Accurate Latency Prediction of Neural Network Model Inference on Edge Devices
- 1 March 2024
- Published by Springer Nature
- p. 42-55
Dynamic Liveness Detection Based on Fusion of mmWave Radar and Vision
- 1 March 2024
- Published by Springer Nature
- p. 42-55
Dynamic Liveness Detection Based on Fusion of mmWave Radar and Vision