Zerui Shao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zerui Shao has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Yi Zhang
Sichuan University
5 shared publications - Beibei Li
School of Cyber Science and Engineering, Sichuan University, Chengdu, China
4 shared publications - Peiran Wang
Tsinghua University, Beijing, China
2 shared publications - Yongqiang Huang
School of Cyber Science and Engineering, Sichuan University, Chengdu, Sichuan, China, Tianfu Jiangxi Laboratory, Chengdu, Sichuan, China, and Key Laboratory of Data Protection and Intelligent Management (Sichuan University), Ministry of Education, Chengdu, Sichuan, China
2 shared publications - Zexin Lu
College of Computer Science, Sichuan University, Chengdu, Sichuan, China
2 shared publications - Ziyuan Yang
Sichuan University
2 shared publications
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5275-5285
Beyond Class Boundaries: Federated Visual Primitive Sharing with Text-Guided Adaptation
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5275-5285
Open AccessBeyond Class Boundaries: Federated Visual Primitive Sharing with Text-Guided Adaptation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (5) , 1-18
PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (5) , 1-18
PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 807-816
FedRIR: Rethinking Information Representation in Federated Learning
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 807-816
Open AccessFedRIR: Rethinking Information Representation in Federated Learning
- 6 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 36 (5) , 994-1010
FedLoRE: Communication-Efficient and Personalized Edge Intelligence Framework via Federated Low-Rank Estimation
Federated learning (FL) has recently garnered significant attention in edge intelligence. However, FL faces two major challenges: First, statistical heterogeneity can adversely impact the performance of the global model on each client. Second, the model transmission between server and clients leads to substantial communication overhead. Previous works often suffer from the trade-off issue between these seemingly competing goals, yet we show that it is possible to address both challenges simultaneously. We propose a novel communication-efficient personalized FL framework for edge intelligence that estimates the low-rank component of the training model gradient and stores the residual component at each client. The low-rank components obtained across communication rounds have high similarity, and sharing these components with the server can significantly reduce communication overhead. Specifically, we highlight the importance of previously neglected residual components in tackling statistical heterogeneity, and retaining them locally for training model updates can effectively improve the personalization performance. Moreover, we provide a theoretical analysis of the convergence guarantee of our framework. Extensive experimental results demonstrate that our framework outperforms state-of-the-art approaches, achieving up to 89.18% reduction in communication overhead and 91.00% reduction in computation overhead while maintaining comparable personalization accuracy compared to previous works.
- 6 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 36 (5) , 994-1010
FedLoRE: Communication-Efficient and Personalized Edge Intelligence Framework via Federated Low-Rank Estimation
Federated learning (FL) has recently garnered significant attention in edge intelligence. However, FL faces two major challenges: First, statistical heterogeneity can adversely impact the performance of the global model on each client. Second, the model transmission between server and clients leads to substantial communication overhead. Previous works often suffer from the trade-off issue between these seemingly competing goals, yet we show that it is possible to address both challenges simultaneously. We propose a novel communication-efficient personalized FL framework for edge intelligence that estimates the low-rank component of the training model gradient and stores the residual component at each client. The low-rank components obtained across communication rounds have high similarity, and sharing these components with the server can significantly reduce communication overhead. Specifically, we highlight the importance of previously neglected residual components in tackling statistical heterogeneity, and retaining them locally for training model updates can effectively improve the personalization performance. Moreover, we provide a theoretical analysis of the convergence guarantee of our framework. Extensive experimental results demonstrate that our framework outperforms state-of-the-art approaches, achieving up to 89.18% reduction in communication overhead and 91.00% reduction in computation overhead while maintaining comparable personalization accuracy compared to previous works.
- Open Access
Energizing Federated Learning via Filter-Aware Attention
Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation through a hypernetwork proves effective, yet existing methods fail to personalize local model structures. This leads to redundant parameters struggling to adapt to diverse data distributions. To address these limitations, we propose FedOFA, utilizing personalized orthogonal filter attention for parameter recalibration. The core is the Two-stream Filter-aware Attention (TFA) module, meticulously designed to extract personalized filter-aware attention maps, incorporating Intra-Filter Attention (IntraFa) and Inter-Filter Attention (InterFA) streams. These streams enhance representation capability and explore optimal implicit structures for local models. Orthogonal regularization minimizes redundancy by averting inter-correlation between filters. Furthermore, we introduce an Attention-Guided Pruning Strategy (AGPS) for communication efficiency. AGPS selectively retains crucial neurons while masking redundant ones, reducing communication costs without performance sacrifice. Importantly, FedOFA operates on the server side, incurring no additional computational cost on the client, making it advantageous in communication-constrained scenarios. Extensive experiments validate superior performance over state-of-the-art approaches, with code availability upon paper acceptance.
Open AccessEnergizing Federated Learning via Filter-Aware Attention
Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation through a hypernetwork proves effective, yet existing methods fail to personalize local model structures. This leads to redundant parameters struggling to adapt to diverse data distributions. To address these limitations, we propose FedOFA, utilizing personalized orthogonal filter attention for parameter recalibration. The core is the Two-stream Filter-aware Attention (TFA) module, meticulously designed to extract personalized filter-aware attention maps, incorporating Intra-Filter Attention (IntraFa) and Inter-Filter Attention (InterFA) streams. These streams enhance representation capability and explore optimal implicit structures for local models. Orthogonal regularization minimizes redundancy by averting inter-correlation between filters. Furthermore, we introduce an Attention-Guided Pruning Strategy (AGPS) for communication efficiency. AGPS selectively retains crucial neurons while masking redundant ones, reducing communication costs without performance sacrifice. Importantly, FedOFA operates on the server side, incurring no additional computational cost on the client, making it advantageous in communication-constrained scenarios. Extensive experiments validate superior performance over state-of-the-art approaches, with code availability upon paper acceptance.
- 9 May 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 147, 136-148
Defending Byzantine attacks in ensemble federated learning: A reputation-based phishing approach
- 9 May 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 147, 136-148
Defending Byzantine attacks in ensemble federated learning: A reputation-based phishing approach
- 20 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 112-125
Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling on-the-Fly for Moving Object Detection
Moving object detection is critical for automated video analysis in many vision-related tasks, such as surveillance tracking, video compression coding, etc. Robust Principal Component Analysis (RPCA), as one of the most popular moving object modelling methods, aims to separate the temporallyvarying (i.e., moving) foreground objects from the static background in video, assuming the background frames to be lowrank while the foreground to be spatially sparse. Classic RPCA imposes sparsity of the foreground component using $\ell_1$ -norm, and minimizes the modeling error via $\ell_2$ -norm. We show that such assumptions can be too restrictive in practice, which limits the effectiveness of the classic RPCA, especially when processing videos with dynamic background, camera jitter, camouflaged moving object, etc. In this paper, we propose a novel RPCA-based model, called Hyper RPCA, to detect moving objects on the fly. Different from classic RPCA, the proposed Hyper RPCA jointly applies the maximum correntropy criterion (MCC) for the modeling error, and Laplacian scale mixture (LSM) model for foreground objects. Extensive experiments have been conducted, and the results demonstrate that the proposed Hyper RPCA has competitive performance for foreground detection to the stateof-the-art algorithms on several well-known benchmark datasets.- 20 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 112-125
Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling on-the-Fly for Moving Object Detection
Moving object detection is critical for automated video analysis in many vision-related tasks, such as surveillance tracking, video compression coding, etc. Robust Principal Component Analysis (RPCA), as one of the most popular moving object modelling methods, aims to separate the temporallyvarying (i.e., moving) foreground objects from the static background in video, assuming the background frames to be lowrank while the foreground to be spatially sparse. Classic RPCA imposes sparsity of the foreground component using $\ell_1$ -norm, and minimizes the modeling error via $\ell_2$ -norm. We show that such assumptions can be too restrictive in practice, which limits the effectiveness of the classic RPCA, especially when processing videos with dynamic background, camera jitter, camouflaged moving object, etc. In this paper, we propose a novel RPCA-based model, called Hyper RPCA, to detect moving objects on the fly. Different from classic RPCA, the proposed Hyper RPCA jointly applies the maximum correntropy criterion (MCC) for the modeling error, and Laplacian scale mixture (LSM) model for foreground objects. Extensive experiments have been conducted, and the results demonstrate that the proposed Hyper RPCA has competitive performance for foreground detection to the stateof-the-art algorithms on several well-known benchmark datasets.