Zhizhong Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhizhong Tan has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Wenyong Wang
School of Computer Science and Engineering, Macau University of Science and Technology, Macau 999078, China
3 shared publications - Mudi Xu
School of Computer Science and Engineering, Macau University of Science and Technology, Macau 999078, China
2 shared publications Anyu Wang
Tanka Inc
1 shared publication- Benfeng Chen
AI Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 510000, China
1 shared publication - Bin Liu
Southwestern University of Finance and Economics
1 shared publication - Guosheng Yin
Department of Statistics and Actuarial Science, The University of Hong Kong
1 shared publication
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (6) , 12939-12955
A Framework for Data Trans-Border Compliance Management Based on Customized Verifiable Credentials
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (6) , 12939-12955
A Framework for Data Trans-Border Compliance Management Based on Customized Verifiable Credentials
- Open Access
Graph Privacy: A Heterogeneous Federated GNN for Trans-Border Financial Data Circulation
The sharing of external data has become a strong demand of financial institutions, but the privacy issue has led to the difficulty of interconnecting different platforms and the low degree of data openness. To effectively solve the privacy problem of financial data in trans-border flow and sharing, to ensure that the data is available but not visible, to realize the joint portrait of all kinds of heterogeneous data of business organizations in different industries, we propose a Heterogeneous Federated Graph Neural Network (HFGNN) approach. In this method, the distribution of heterogeneous business data of trans-border organizations is taken as subgraphs, and the sharing and circulation process among subgraphs is constructed as a statistically heterogeneous global graph through a central server. Each subgraph learns the corresponding personalized service model through local training to select and update the relevant subset of subgraphs with aggregated parameters, and effectively separates and combines topological and feature information among subgraphs. Finally, our simulation experimental results show that the proposed method has higher accuracy performance and faster convergence speed than existing methods.
Open AccessGraph Privacy: A Heterogeneous Federated GNN for Trans-Border Financial Data Circulation
The sharing of external data has become a strong demand of financial institutions, but the privacy issue has led to the difficulty of interconnecting different platforms and the low degree of data openness. To effectively solve the privacy problem of financial data in trans-border flow and sharing, to ensure that the data is available but not visible, to realize the joint portrait of all kinds of heterogeneous data of business organizations in different industries, we propose a Heterogeneous Federated Graph Neural Network (HFGNN) approach. In this method, the distribution of heterogeneous business data of trans-border organizations is taken as subgraphs, and the sharing and circulation process among subgraphs is constructed as a statistically heterogeneous global graph through a central server. Each subgraph learns the corresponding personalized service model through local training to select and update the relevant subset of subgraphs with aggregated parameters, and effectively separates and combines topological and feature information among subgraphs. Finally, our simulation experimental results show that the proposed method has higher accuracy performance and faster convergence speed than existing methods.
- Open Access
- 27 June 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (13) , 5593
AHAC: Advanced Network-Hiding Access Control Framework
In the current context of rapid Internet of Things (IoT) and cloud computing technology development, the Single Packet Authorization (SPA) protocol faces increasing challenges, such as security threats from Distributed Denial of Service (DDoS) attacks. To address these issues, we propose the Advanced Network-Hiding Access Control (AHAC) framework, designed to enhance security by reducing network environment exposure and providing secure access methods. AHAC introduces an independent control surface as the access proxy service and combines it with a noise generation mechanism for encrypted access schemes, replacing the traditional RSA signature method used in SPA protocols. This framework significantly improves system security, reduces computational costs, and enhances key verification efficiency. The AHAC framework addresses several limitations inherent in SPA: users need to know the IP address of resources in advance, exposing the resource address to potential attacks; SPA’s one-way authentication mechanism is insufficient for multi-level authentication in dynamic environments; deploying the knocking module and protected resources on the same host can lead to resource exhaustion and service unavailability under heavy loads; and SPA often uses high-overhead encryption algorithms like RSA2048. To counter these limitations, AHAC separates the Port Knocking module from the access control module, supports mutual authentication, and implements an extensible two-way communication mechanism. It also employs ECC and ECDH algorithms, enhancing security while reducing computational costs. We conducted extensive experiments to validate AHAC’s performance, high availability, extensibility, and compatibility. The experiments compared AHAC with traditional SPA in terms of time cost and performance.
- 27 June 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (13) , 5593
Open AccessAHAC: Advanced Network-Hiding Access Control Framework
In the current context of rapid Internet of Things (IoT) and cloud computing technology development, the Single Packet Authorization (SPA) protocol faces increasing challenges, such as security threats from Distributed Denial of Service (DDoS) attacks. To address these issues, we propose the Advanced Network-Hiding Access Control (AHAC) framework, designed to enhance security by reducing network environment exposure and providing secure access methods. AHAC introduces an independent control surface as the access proxy service and combines it with a noise generation mechanism for encrypted access schemes, replacing the traditional RSA signature method used in SPA protocols. This framework significantly improves system security, reduces computational costs, and enhances key verification efficiency. The AHAC framework addresses several limitations inherent in SPA: users need to know the IP address of resources in advance, exposing the resource address to potential attacks; SPA’s one-way authentication mechanism is insufficient for multi-level authentication in dynamic environments; deploying the knocking module and protected resources on the same host can lead to resource exhaustion and service unavailability under heavy loads; and SPA often uses high-overhead encryption algorithms like RSA2048. To counter these limitations, AHAC separates the Port Knocking module from the access control module, supports mutual authentication, and implements an extensible two-way communication mechanism. It also employs ECC and ECDH algorithms, enhancing security while reducing computational costs. We conducted extensive experiments to validate AHAC’s performance, high availability, extensibility, and compatibility. The experiments compared AHAC with traditional SPA in terms of time cost and performance.
- Open Access
Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network
This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limitations of existing methods that lack financial theory guidance and ignore various trend signals and their interactions. We propose three heterogeneous tasks, including price moving average regression, price gap regression and change-point detection to trace the short-, intermediate-, and long-term trend factors present in the data. In addition, this study also considers the cross-sectional correlation characteristics of future contracts, where prices of different futures often show strong dynamic correlations. Each variable (future contract) depends not only on its historical values (temporal) but also on the observation of other variables (cross-sectional). To capture these dynamic relationships more accurately, we resort to the spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. The model employs a continuous learning strategy to simultaneously consider these tasks (factors). Additionally, due to the heterogeneity of the tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features to mitigate the catastrophic forgetting (CF) problem. Empirical tests on 49 commodity futures in China's futures market demonstrate that the proposed model outperforms other state-of-the-art models in terms of prediction accuracy. Not only does this research promote the integration of financial theory and deep learning, but it also provides a scientific basis for actual trading decisions.
Open AccessFutures Quantitative Investment with Heterogeneous Continual Graph Neural Network
This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limitations of existing methods that lack financial theory guidance and ignore various trend signals and their interactions. We propose three heterogeneous tasks, including price moving average regression, price gap regression and change-point detection to trace the short-, intermediate-, and long-term trend factors present in the data. In addition, this study also considers the cross-sectional correlation characteristics of future contracts, where prices of different futures often show strong dynamic correlations. Each variable (future contract) depends not only on its historical values (temporal) but also on the observation of other variables (cross-sectional). To capture these dynamic relationships more accurately, we resort to the spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. The model employs a continuous learning strategy to simultaneously consider these tasks (factors). Additionally, due to the heterogeneity of the tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features to mitigate the catastrophic forgetting (CF) problem. Empirical tests on 49 commodity futures in China's futures market demonstrate that the proposed model outperforms other state-of-the-art models in terms of prediction accuracy. Not only does this research promote the integration of financial theory and deep learning, but it also provides a scientific basis for actual trading decisions.