Chen Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Chen Zhang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Xin Fu
University of Houston
2 shared publications - Aamir Bader Shah
Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA
1 shared publication - Chenhao Xie
Beihang University, Beijing, China
1 shared publication - Jiefu Chen
Department of Electrical and Computer Engineering University of Houston Houston Texas USA
1 shared publication - Lening Wang
Department of Computer Science, Prairie View A&M University, Prairie View, TX 77446, USA
1 shared publication - Ruizhi Cao
School of Computer Science and Engineering, Beihang University, Beijing, China
1 shared publication
Latest Publications
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Computing
- Vol. 11 (2) , 147-157
Importance Aware Undervolting for Robust Neural Network Training
Convolutional Neural Network (CNN) is a powerful tool that has been extensively applied to many different applications. However, recent developments at CNN have revealed its vulnerability against adversarial example attacks. By introducing visually undetectable noise to the input image, an adversarial example attack can cause the CNN classifier to make false predictions. Multiple approaches have been proposed to defend against adversarial samples, one of which focuses on injecting noise into CNN during training. However, the existing method cannot generate noise efficiently and introduces extra time and energy overhead. In this paper, we propose an Importance-Aware undervolting training framework to improve CNN robustness. The undervolting technique is employed during training for noise generation at negligible overhead. Meanwhile, we observe that the neuron importance and bit importance in hardware can be leveraged during undervolting CNN training for controllable and flexible noise injection, which improves robustness. We design a position-aware bit mapping method in the memory unit by allocating data bits based on significance. And an importanceaware processing element (PE) mapping is also proposed at the computation unit for noise restriction. Our approach regularizes the noise injected into CNN and serves as an efficient method to defend against adversarial example attacks with significant energy savings. The proposed framework is evaluated through both FPGA implementation and software simulation. The experiment results show that our importance-aware undervolting CNN training achieves 47.8% adversarial accuracy at PGD-10 attack and 47.0% training energy savings.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Sustainable Computing
- Vol. 11 (2) , 147-157
Importance Aware Undervolting for Robust Neural Network Training
Convolutional Neural Network (CNN) is a powerful tool that has been extensively applied to many different applications. However, recent developments at CNN have revealed its vulnerability against adversarial example attacks. By introducing visually undetectable noise to the input image, an adversarial example attack can cause the CNN classifier to make false predictions. Multiple approaches have been proposed to defend against adversarial samples, one of which focuses on injecting noise into CNN during training. However, the existing method cannot generate noise efficiently and introduces extra time and energy overhead. In this paper, we propose an Importance-Aware undervolting training framework to improve CNN robustness. The undervolting technique is employed during training for noise generation at negligible overhead. Meanwhile, we observe that the neuron importance and bit importance in hardware can be leveraged during undervolting CNN training for controllable and flexible noise injection, which improves robustness. We design a position-aware bit mapping method in the memory unit by allocating data bits based on significance. And an importanceaware processing element (PE) mapping is also proposed at the computation unit for noise restriction. Our approach regularizes the noise injected into CNN and serves as an efficient method to defend against adversarial example attacks with significant energy savings. The proposed framework is evaluated through both FPGA implementation and software simulation. The experiment results show that our importance-aware undervolting CNN training achieves 47.8% adversarial accuracy at PGD-10 attack and 47.0% training energy savings.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (6) , 2073-2086
AR-Light: Enabling Fast and Lightweight Multi-User Augmented Reality via Semantic Segmentation and Collaborative View Synchronization
Multi-user Augmented Reality (MuAR) allows multiple users to interact with shared virtual objects, facilitated by exchanging environment information. Current MuAR systems rely on 3D point clouds for real-world analysis, view synchronization, object rendering, and movement tracking. However, the complexity of 3D point clouds leads to significant processing delays, with approximately 80% of overhead in commercial frameworks. This hampers usability and degrades user experience. Our analysis reveals that maintaining the facing side of the real-world scene in a stable environment provides sufficient information for virtual object placement and rendering. To address this, we introduce a lightweight quadtree structure, representing 2D scenes through semantic segmentation and geometry, as an alternative to 3D point clouds. Additionally, we propose a novel correction method to handle potential shifts in virtual object placement during view synchronization among users. Combining all designs, we implement a fast and lightweight MuAR framework named AR-Light and test our framework on commercial AR devices. The evaluation results on real-world applications demonstrate that AR-Light can achieve high performance in various real-world scenes while maintaining a comparable virtual object placement accuracy.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (6) , 2073-2086
AR-Light: Enabling Fast and Lightweight Multi-User Augmented Reality via Semantic Segmentation and Collaborative View Synchronization
Multi-user Augmented Reality (MuAR) allows multiple users to interact with shared virtual objects, facilitated by exchanging environment information. Current MuAR systems rely on 3D point clouds for real-world analysis, view synchronization, object rendering, and movement tracking. However, the complexity of 3D point clouds leads to significant processing delays, with approximately 80% of overhead in commercial frameworks. This hampers usability and degrades user experience. Our analysis reveals that maintaining the facing side of the real-world scene in a stable environment provides sufficient information for virtual object placement and rendering. To address this, we introduce a lightweight quadtree structure, representing 2D scenes through semantic segmentation and geometry, as an alternative to 3D point clouds. Additionally, we propose a novel correction method to handle potential shifts in virtual object placement during view synchronization among users. Combining all designs, we implement a fast and lightweight MuAR framework named AR-Light and test our framework on commercial AR devices. The evaluation results on real-world applications demonstrate that AR-Light can achieve high performance in various real-world scenes while maintaining a comparable virtual object placement accuracy.