Fan Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fan Yang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Lvyang Ye
Xian Institute of Electromechanical Information Technology, Xian, China
2 shared publications - Yanan Qiao
The School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, China
2 shared publications Zimo Wen
Xi’an Jiaotong University
2 shared publications- Boran Zhao
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, School of Software Engineering, Xian, Shaanxi, China
1 shared publication Hetian Liu
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, School of Software Engineering, Xian, Shaanxi, China
1 shared publication- Hongjie Liu
School of Computer Science and Technology, Xian Jiaotong University, Xian, China
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) , 13216-13233
Secure Interoperability for Decentralized Credit Ecosystems: Achieving Data Confidentiality and Integrity Across Chains
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (6) , 13216-13233
Secure Interoperability for Decentralized Credit Ecosystems: Achieving Data Confidentiality and Integrity Across Chains
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 73 (6) , 4259-4270
AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training
Training deep neural networks (DNNs) on edge devices faces challenges due to the large-scale datasets required, which are costly for edge devices, especially in large language model (LLM) tasks. To address this, a DNN-free method called Near-Memory Sampling (NMS) has been introduced. NMS reduces dimensionality and performs exemplar sampling in the reduced space, avoiding architectural bias and improving generalization. However, NMS has two limitations: 1) The mismatch between the search method and the non-monotonic property of the perplexity error function leads to the emergence of outliers; 2) Key parameter (i.e., target perplexity) is selected empirically, introducing arbitrariness and leading to uneven sampling. These two issues lead to representative bias of exemplars, resulting in degraded accuracy. To overcome these, we propose AdapSNE, which integrates the Fireworks Algorithm (FWA) for efficient non-monotonic search to avoid outliers and uses entropy-guided optimization for uniform sampling, ensuring representative training samples. To reduce the cost of iterative computations, we design an accelerator with custom dataflow and time-multiplexing mechanisms. Experimental results show that AdapSNE outperforms state-of-the-art methods, including both DNN-based (DQAS) and DNN-free (NMS) approaches, across small-scale image datasets, large-scale datasets, and the MMLU benchmark for LLM tasks.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 73 (6) , 4259-4270
AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training
Training deep neural networks (DNNs) on edge devices faces challenges due to the large-scale datasets required, which are costly for edge devices, especially in large language model (LLM) tasks. To address this, a DNN-free method called Near-Memory Sampling (NMS) has been introduced. NMS reduces dimensionality and performs exemplar sampling in the reduced space, avoiding architectural bias and improving generalization. However, NMS has two limitations: 1) The mismatch between the search method and the non-monotonic property of the perplexity error function leads to the emergence of outliers; 2) Key parameter (i.e., target perplexity) is selected empirically, introducing arbitrariness and leading to uneven sampling. These two issues lead to representative bias of exemplars, resulting in degraded accuracy. To overcome these, we propose AdapSNE, which integrates the Fireworks Algorithm (FWA) for efficient non-monotonic search to avoid outliers and uses entropy-guided optimization for uniform sampling, ensuring representative training samples. To reduce the cost of iterative computations, we design an accelerator with custom dataflow and time-multiplexing mechanisms. Experimental results show that AdapSNE outperforms state-of-the-art methods, including both DNN-based (DQAS) and DNN-free (NMS) approaches, across small-scale image datasets, large-scale datasets, and the MMLU benchmark for LLM tasks.
- 23 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (3) , 1933-1948
Blockchain-Empowered AI for Fintech Services Computing: A Verifiable Framework for Transparent and Sustainable Credit Risk Assessment
In the era of fintech services computing, the convergence of advanced technologies has become pivotal for driving innovation. The seamless integration of IIoT-enabled data streams with artificial intelligence (AI) systems presents unprecedented opportunities for revolutionizing financial risk assessment. Efficient AI-to-AI business platforms are crucial for sustainable and transparent fintech credit risk analysis. However, current practices rely on single AI models, leading to inefficiencies and regulatory challenges. This paper proposes a novel Blockchain Regulatory Framework to address these issues, particularly in lending to small and micro enterprises. The key novelty of our work, compared to existing state-of-the-art, is fourfold: 1) a multi-level guarantee strategy that combines blockchain with AI-AI models to enable distributed risk-sharing among guarantee agencies; 2) a dual-chain blockchain structure for secure and efficient storage of credit data and processes; 3) the integration of Intel SGX with Oblivious RAM (ORAM) to ensure unprecedented confidentiality, integrity, and availability in credit data sharing; and 4) the incorporation of game theory to mathematically validate the anti-collusion properties of the AI-AI decision mechanism. Our findings indicate that the proposed framework offers a comprehensive solution for achieving safe, efficient, and transparent credit assessments. This approach holds significant promise for developing effective financing solutions while ensuring data security, regulatory compliance, and robust credit evaluation methodologies.
- 23 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (3) , 1933-1948
Blockchain-Empowered AI for Fintech Services Computing: A Verifiable Framework for Transparent and Sustainable Credit Risk Assessment
In the era of fintech services computing, the convergence of advanced technologies has become pivotal for driving innovation. The seamless integration of IIoT-enabled data streams with artificial intelligence (AI) systems presents unprecedented opportunities for revolutionizing financial risk assessment. Efficient AI-to-AI business platforms are crucial for sustainable and transparent fintech credit risk analysis. However, current practices rely on single AI models, leading to inefficiencies and regulatory challenges. This paper proposes a novel Blockchain Regulatory Framework to address these issues, particularly in lending to small and micro enterprises. The key novelty of our work, compared to existing state-of-the-art, is fourfold: 1) a multi-level guarantee strategy that combines blockchain with AI-AI models to enable distributed risk-sharing among guarantee agencies; 2) a dual-chain blockchain structure for secure and efficient storage of credit data and processes; 3) the integration of Intel SGX with Oblivious RAM (ORAM) to ensure unprecedented confidentiality, integrity, and availability in credit data sharing; and 4) the incorporation of game theory to mathematically validate the anti-collusion properties of the AI-AI decision mechanism. Our findings indicate that the proposed framework offers a comprehensive solution for achieving safe, efficient, and transparent credit assessments. This approach holds significant promise for developing effective financing solutions while ensuring data security, regulatory compliance, and robust credit evaluation methodologies.
- 20 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (15) , 31064-31077
Enhanced Traffic Carbon Emissions Data Sharing and Modeling via Blockchain and Personalized Federated Learning in IIoT Ecosystem
The energy transition is essential for achieving sustainable development, and in this context, sharing traffic carbon emissions data within the IIoT ecosystem plays a pivotal role in incentivizing the reduction of greenhouse gas emissions and promoting cleaner transportation solutions. By leveraging interconnected IoT devices and data analytics, we can enhance transparency and collaboration, driving more effective strategies for sustainable transportation. However, managing traffic carbon emissions and facilitating the complex sharing of emission data across various entities present significant challenges. To address these issues, we propose a blockchain-based traffic carbon data sharing and modeling (BCSM) method that provides a secure, efficient, and reliable platform for carbon emissions trading. Our approach introduces a blockchain-based framework designed to ensure data integrity and user privacy in carbon markets, thereby enhancing transparency and trust among participants. We further develop a hierarchical aggregated carbon trading data modeling architecture that integrates hypernetworks with attention mechanisms, enabling the creation of high-quality, personalized models for federated learning clients. This architecture allows clients to benefit from collective insights while preserving data confidentiality. Additionally, we implement a blockchain-editable access control mechanism, facilitating fine-grained permissions management and maintaining a comprehensive, auditable trail of system interactions. The experimental results demonstrate that our BCSM approach not only enhances data security but also significantly improves model performance, offering a robust solution to the challenges in traffic carbon trading and contributing to the broader energy transition objectives.
- 20 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (15) , 31064-31077
Enhanced Traffic Carbon Emissions Data Sharing and Modeling via Blockchain and Personalized Federated Learning in IIoT Ecosystem
The energy transition is essential for achieving sustainable development, and in this context, sharing traffic carbon emissions data within the IIoT ecosystem plays a pivotal role in incentivizing the reduction of greenhouse gas emissions and promoting cleaner transportation solutions. By leveraging interconnected IoT devices and data analytics, we can enhance transparency and collaboration, driving more effective strategies for sustainable transportation. However, managing traffic carbon emissions and facilitating the complex sharing of emission data across various entities present significant challenges. To address these issues, we propose a blockchain-based traffic carbon data sharing and modeling (BCSM) method that provides a secure, efficient, and reliable platform for carbon emissions trading. Our approach introduces a blockchain-based framework designed to ensure data integrity and user privacy in carbon markets, thereby enhancing transparency and trust among participants. We further develop a hierarchical aggregated carbon trading data modeling architecture that integrates hypernetworks with attention mechanisms, enabling the creation of high-quality, personalized models for federated learning clients. This architecture allows clients to benefit from collective insights while preserving data confidentiality. Additionally, we implement a blockchain-editable access control mechanism, facilitating fine-grained permissions management and maintaining a comprehensive, auditable trail of system interactions. The experimental results demonstrate that our BCSM approach not only enhances data security but also significantly improves model performance, offering a robust solution to the challenges in traffic carbon trading and contributing to the broader energy transition objectives.