Xiuhua Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xiuhua Wang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Shuai Wang
National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China
5 shared publications - Yiwei Li
Fujian Key Laboratory of Communication Network and Information Processing, Xiamen University of Technology, Xiamen, China
4 shared publications - Fengrui Fan
Huazhong University of Science and Technology
2 shared publications - Shikang Li
Huazhong University of Science and Technology
2 shared publications - Yu Zheng
University of California, Irvine, Irvine, CA, USA
2 shared publications - Chong Fu
School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China
1 shared publication
Latest Publications
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 8225-8238
Federated Learning With Enhanced Privacy via Model Splitting and Random Client Participation
Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-splitting privacy-amplified federated learning (MS-PAFL), a novel framework that combines structural model splitting with statistical privacy amplification. In this framework, each client’s model is partitioned into a private submodel, retained locally, and a public submodel, released for global aggregation. The calibrated Gaussian noise is injected only into the public submodel, thereby confining its adverse impact while preserving the utility of the retained local model components. We further present a rigorous theoretical analysis that characterizes the joint privacy amplification achieved through random client participation and local data subsampling under this architecture. The analysis provides explicit bounds on both single-round and total privacy loss, demonstrating that MS-PAFL significantly reduces the noise necessary to satisfy a target privacy protection level. Extensive experiments validate our theoretical findings, showing that MS-PAFL consistently attains a superior privacy–utility trade-off compared with conventional DP-FL baselines and enables the training of highly accurate models under strong privacy guarantees.
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 8225-8238
Federated Learning With Enhanced Privacy via Model Splitting and Random Client Participation
Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-splitting privacy-amplified federated learning (MS-PAFL), a novel framework that combines structural model splitting with statistical privacy amplification. In this framework, each client’s model is partitioned into a private submodel, retained locally, and a public submodel, released for global aggregation. The calibrated Gaussian noise is injected only into the public submodel, thereby confining its adverse impact while preserving the utility of the retained local model components. We further present a rigorous theoretical analysis that characterizes the joint privacy amplification achieved through random client participation and local data subsampling under this architecture. The analysis provides explicit bounds on both single-round and total privacy loss, demonstrating that MS-PAFL significantly reduces the noise necessary to satisfy a target privacy protection level. Extensive experiments validate our theoretical findings, showing that MS-PAFL consistently attains a superior privacy–utility trade-off compared with conventional DP-FL baselines and enables the training of highly accurate models under strong privacy guarantees.
- 20 October 2025
- Published by Springer Nature
- p. 403-423
Improving Byzantine-Resilience in Federated Learning via Diverse Aggregation and Adaptive Variance Reduction
- 20 October 2025
- Published by Springer Nature
- p. 403-423
Improving Byzantine-Resilience in Federated Learning via Diverse Aggregation and Adaptive Variance Reduction
- Open Access
Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation
Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-splitting privacy-amplified federated learning (MS-PAFL), a novel framework that combines structural model splitting with statistical privacy amplification. In this framework, each client's model is partitioned into a private submodel, retained locally, and a public submodel, shared for global aggregation. The calibrated Gaussian noise is injected only into the public submodel, thereby confining its adverse impact while preserving the utility of the local model. We further present a rigorous theoretical analysis that characterizes the joint privacy amplification achieved through random client participation and local data subsampling under this architecture. The analysis provides tight bounds on both single-round and total privacy loss, demonstrating that MS-PAFL significantly reduces the noise necessary to satisfy a target privacy protection level. Extensive experiments validate our theoretical findings, showing that MS-PAFL consistently attains a superior privacy-utility trade-off and enables the training of highly accurate models under strong privacy guarantees.
Open AccessFederated Learning with Enhanced Privacy via Model Splitting and Random Client Participation
Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-splitting privacy-amplified federated learning (MS-PAFL), a novel framework that combines structural model splitting with statistical privacy amplification. In this framework, each client's model is partitioned into a private submodel, retained locally, and a public submodel, shared for global aggregation. The calibrated Gaussian noise is injected only into the public submodel, thereby confining its adverse impact while preserving the utility of the local model. We further present a rigorous theoretical analysis that characterizes the joint privacy amplification achieved through random client participation and local data subsampling under this architecture. The analysis provides tight bounds on both single-round and total privacy loss, demonstrating that MS-PAFL significantly reduces the noise necessary to satisfy a target privacy protection level. Extensive experiments validate our theoretical findings, showing that MS-PAFL consistently attains a superior privacy-utility trade-off and enables the training of highly accurate models under strong privacy guarantees.
- 3 May 2025
- Published by Springer Nature
- p. 191-210
Efficient and Verifiable Multi-server Framework for Secure Information Classification and Storage
- 3 May 2025
- Published by Springer Nature
- p. 191-210
Efficient and Verifiable Multi-server Framework for Secure Information Classification and Storage
- 16 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (3) , 2227-2242
Attribute-Based Access Control Encryption
The burgeoning complexity of communication necessitates a high demand for security. Access control encryption is a promising primitive to meet the security demand but the bulk of its constructions rely on formulating the access control policy with identities. Attribute-based access control policy in attribute-based encryption (ABE) is known to be more expressive without relying on enumerating identities. We propose a generic framework to build attribute-based access control encryption from ciphertext-policy ABE. Our instantiations prioritize different emphases on expressiveness and efficiency. The first instantiation supports multi-valued AND-gate access control structures, while the second supports the linear-secret-sharing access structure. Both are prototyped with efficiency validated empirically.
- 16 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (3) , 2227-2242
Attribute-Based Access Control Encryption
The burgeoning complexity of communication necessitates a high demand for security. Access control encryption is a promising primitive to meet the security demand but the bulk of its constructions rely on formulating the access control policy with identities. Attribute-based access control policy in attribute-based encryption (ABE) is known to be more expressive without relying on enumerating identities. We propose a generic framework to build attribute-based access control encryption from ciphertext-policy ABE. Our instantiations prioritize different emphases on expressiveness and efficiency. The first instantiation supports multi-valued AND-gate access control structures, while the second supports the linear-secret-sharing access structure. Both are prototyped with efficiency validated empirically.
- 21 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (12) , 6369-6384
Differentially Private and Heterogeneity-Robust Federated Learning With Theoretical Guarantee
Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients’ private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients’ privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this paper, we propose a differentially private and heterogeneity-robust FL algorithm, named DP-FedCVR to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed DP-FedCVR algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that DP-FedCVR provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets.
- 21 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (12) , 6369-6384
Differentially Private and Heterogeneity-Robust Federated Learning With Theoretical Guarantee
Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients’ private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients’ privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this paper, we propose a differentially private and heterogeneity-robust FL algorithm, named DP-FedCVR to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed DP-FedCVR algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that DP-FedCVR provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets.
- Open Access
- 16 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (9) , 1-23
Encrypted Video Search with Single/Multiple Writers
Video-based services have become popular. Clients often outsource their videos to the cloud to relieve local maintenance. However, privacy has become a major concern, since many videos contain sensitive information. Although retrieving (unencrypted) videos has been extensively investigated, retrieving encrypted multimedia has received relatively rare attention, at best in a limitation of image-based similarity searches. We initiate the study of scalable encrypted video search, enabling clients to query videos similar to an image search. Our modular framework leverages intrinsic attributes of videos, such as semantics and visuals, to effectively capture their contents. We propose a two-step approach whereby lightweight searchable encryption techniques are used for pre-screening, followed by an interactive approach for fine-grained search. Furthermore, we present three instantiations, including one centralized-writer instantiation and two distributed-writer instantiations, to effectively cater to varying needs and scenarios: (1) The centralized one employs forward and backward private searchable encryption [CCS 2017] over deep hashing [CVPR 2020]. (2) Motivated by distributed computing, the multi-writer instantiations building atop HSE [Usenix Security 2022] allows searching the relevant videos contributed by multiple intuitions collaboratively. Our experimental results illustrate their practical performance over multiple real-world datasets, whether in a centralized setting or distributed setting.
- 16 August 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (9) , 1-23
Open AccessEncrypted Video Search with Single/Multiple Writers
Video-based services have become popular. Clients often outsource their videos to the cloud to relieve local maintenance. However, privacy has become a major concern, since many videos contain sensitive information. Although retrieving (unencrypted) videos has been extensively investigated, retrieving encrypted multimedia has received relatively rare attention, at best in a limitation of image-based similarity searches. We initiate the study of scalable encrypted video search, enabling clients to query videos similar to an image search. Our modular framework leverages intrinsic attributes of videos, such as semantics and visuals, to effectively capture their contents. We propose a two-step approach whereby lightweight searchable encryption techniques are used for pre-screening, followed by an interactive approach for fine-grained search. Furthermore, we present three instantiations, including one centralized-writer instantiation and two distributed-writer instantiations, to effectively cater to varying needs and scenarios: (1) The centralized one employs forward and backward private searchable encryption [CCS 2017] over deep hashing [CVPR 2020]. (2) Motivated by distributed computing, the multi-writer instantiations building atop HSE [Usenix Security 2022] allows searching the relevant videos contributed by multiple intuitions collaboratively. Our experimental results illustrate their practical performance over multiple real-world datasets, whether in a centralized setting or distributed setting.