Huang Zeng
Research Subjects
Research Interests
Huang Zeng has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Anjia Yang
Jinan University
2 shared publications - Jian Weng
Guangzhou University
2 shared publications - Yi Liu
Jinan University
2 shared publications Zilin Liu
Shiqi District Taxation Branch of Zhongshan Municipal Taxation Bureau
2 shared publications- Fengjun Xiao
Zhejiang Informatization Development Institute, Hangzhou Dianzi University, Hangzhou, China
1 shared publication Min-Rong Chen
South China Normal University
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 12333-12348
GMHL: Generalized Multi-Hop Locks for Privacy-Preserving Payment Channel Networks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 12333-12348
GMHL: Generalized Multi-Hop Locks for Privacy-Preserving Payment Channel Networks
- 12 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (1) , 577-589
Publicly Auditable Federated Learning With Privacy and Byzantine Robustness
Federated learning (FL) is a machine learning paradigm that can break the data silo effect, and it has been applied by lots of enterprises to train models that are deployed in inference services. However, existing FL schemes hardly support users who purchase inference services in auditing the training process, as the requirements for privacy and robustness restrict the realization of public auditability. This makes it difficult to allay users' doubts about whether the model is trained correctly. In this paper, we propose a publicly auditable and secure federated learning, which enables anyone to audit the correctness of model training securely. Specifically, we design a series of algorithms for generating the multiplication-related random vector, based on which we design a protocol that can generate the training record with masked privacy information for Byzantine-robust FL. The service provider can disclose the training record when the model is outputted, enabling users to reproduce the training process for auditing purpose without the need to know the privacy data of all parties involved in the FL. Meanwhile, to ensure model accuracy, we design an auditable incentive mechanism and a privacy-preserving federation member selection protocol to motivate workers to execute model training correctly. We analyze the security of our scheme and evaluate its efficiency. Compared to existing schemes requiring $O(R)$ smart contract calls, our scheme requires only 3 calls. Also, experimental results under different settings show that the scheme is efficient and Byzantine-robust.
- 12 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (1) , 577-589
Publicly Auditable Federated Learning With Privacy and Byzantine Robustness
Federated learning (FL) is a machine learning paradigm that can break the data silo effect, and it has been applied by lots of enterprises to train models that are deployed in inference services. However, existing FL schemes hardly support users who purchase inference services in auditing the training process, as the requirements for privacy and robustness restrict the realization of public auditability. This makes it difficult to allay users' doubts about whether the model is trained correctly. In this paper, we propose a publicly auditable and secure federated learning, which enables anyone to audit the correctness of model training securely. Specifically, we design a series of algorithms for generating the multiplication-related random vector, based on which we design a protocol that can generate the training record with masked privacy information for Byzantine-robust FL. The service provider can disclose the training record when the model is outputted, enabling users to reproduce the training process for auditing purpose without the need to know the privacy data of all parties involved in the FL. Meanwhile, to ensure model accuracy, we design an auditable incentive mechanism and a privacy-preserving federation member selection protocol to motivate workers to execute model training correctly. We analyze the security of our scheme and evaluate its efficiency. Compared to existing schemes requiring $O(R)$ smart contract calls, our scheme requires only 3 calls. Also, experimental results under different settings show that the scheme is efficient and Byzantine-robust.