Siwan Noh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Siwan Noh has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Kyung-Hyune Rhee
Division of Computer Engineering and AI, Pukyong National University, Busan 48513, Republic of Korea
13 shared publications - Muhammad Firdaus
Pukyong National University
4 shared publications - Sang Uk Shin
Division of Computer Engineering and Artificial Intelligence, Pukyong National University, Busan 48513, Republic of Korea
3 shared publications Kyung-Hyune Rhee
Division of Computer Engineering, Pukyong National University
2 shared publicationsMuhammad Firdaus
Department of Information Security, Pukyong National University, Busan, Republic of Korea
2 shared publicationsZhuohao Qian
Pukyong National University
2 shared publications
Latest Publications
- Open Access
- 27 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12568
CoFT: A Fair and Transparent Compensation Framework for Hierarchical Federated Learning
Hierarchical Federated Learning (HFL) requires a scalable and transparent incentive mechanism, yet existing on-chain approaches are too costly and centralized solutions lack trust. To address this, we propose CoFT, a hybrid framework that manages rewards off-chain using a hierarchy of state channels and a stablecoin while securing the system’s integrity with a single on-chain cryptographic anchor. This architecture dramatically reduces on-chain complexity from a prohibitive to a sustainable , enabling cryptographic verifiability, automated trustless payouts, and fair burden-sharing. CoFT thus offers a robust and economically viable blueprint for the financial infrastructure of large-scale, trustworthy collaborative AI ecosystems.- 27 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12568
Open AccessCoFT: A Fair and Transparent Compensation Framework for Hierarchical Federated Learning
Hierarchical Federated Learning (HFL) requires a scalable and transparent incentive mechanism, yet existing on-chain approaches are too costly and centralized solutions lack trust. To address this, we propose CoFT, a hybrid framework that manages rewards off-chain using a hierarchy of state channels and a stablecoin while securing the system’s integrity with a single on-chain cryptographic anchor. This architecture dramatically reduces on-chain complexity from a prohibitive to a sustainable , enabling cryptographic verifiability, automated trustless payouts, and fair burden-sharing. CoFT thus offers a robust and economically viable blueprint for the financial infrastructure of large-scale, trustworthy collaborative AI ecosystems. - Open Access
- 21 December 2024
- Published by Springer Nature in Information Systems Frontiers
Hyperledger Fabric-Powered Network Slicing Handover Authentication
- 21 December 2024
- Published by Springer Nature in Information Systems Frontiers
Open AccessHyperledger Fabric-Powered Network Slicing Handover Authentication
- Open Access
- 10 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Fair Incentive Distribution Mechanism in Hierarchical Federated Learning
The integration of artificial intelligence (AI) in healthcare, powered by Internet of Medical Things (IoMT) data, offers significant potential for personalized and efficient patient care. Hierarchical federated learning (HFL) is a promising approach for healthcare applications, combining cross-silo and cross-device federated learning. This architecture allows hospitals to train local models using patient data, while sharing anonymized parameters with other hospitals to improve diagnosis. However, existing studies on incentive mechanisms in HFL often focus on determining optimal incentive values but neglect the integration of these incentives into the reward stage. Moreover, the two-layer architecture of HFL introduces challenges related to disparities in patient volume and diversity across hospitals. In this paper, we propose a fair incentive distribution mechanism for hierarchical systems using blockchain state channels. We ensure equal incentive budget contributions from all organizations, preventing free-riders in the HFL system with a channel factory solution. Additionally, virtual channels support transactions without intermediaries, minimizing computational costs in the blockchain network.
- 10 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessFair Incentive Distribution Mechanism in Hierarchical Federated Learning
The integration of artificial intelligence (AI) in healthcare, powered by Internet of Medical Things (IoMT) data, offers significant potential for personalized and efficient patient care. Hierarchical federated learning (HFL) is a promising approach for healthcare applications, combining cross-silo and cross-device federated learning. This architecture allows hospitals to train local models using patient data, while sharing anonymized parameters with other hospitals to improve diagnosis. However, existing studies on incentive mechanisms in HFL often focus on determining optimal incentive values but neglect the integration of these incentives into the reward stage. Moreover, the two-layer architecture of HFL introduces challenges related to disparities in patient volume and diversity across hospitals. In this paper, we propose a fair incentive distribution mechanism for hierarchical systems using blockchain state channels. We ensure equal incentive budget contributions from all organizations, preventing free-riders in the HFL system with a channel factory solution. Additionally, virtual channels support transactions without intermediaries, minimizing computational costs in the blockchain network.
- Open Access
- 21 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 133394-133412
A Blockchain-Based Auditable Semi-Asynchronous Federated Learning for Heterogeneous Clients
Federated learning (FL) is a privacy-preserving approach in Artificial Intelligence (AI) that involves exchanging intermediate training parameters instead of raw data, thereby avoiding privacy breaches and promoting effective data collaboration. However, FL still faces several unresolved challenges, including trust issues among participants because traditional FL lacks a mutual consensus auditing mechanism. Another challenge is that when the number of participating nodes is large and resources are heterogeneous; this can lead to low efficiency. To overcome these challenges, we propose a Blockchain-based Auditable Semi-Asynchronous Federated Learning (BASA-FL) system. BASA-FL includes a smart contract that coordinates and records the FL exchange process, enabling the ability to trace and audit the behavior of participating workers. In addition, we proposed an efficient semi-asynchronous approach in blockchain-based distributed FL as the main contribution to addressing heterogeneous problems. We designed a method to quantify worker contributions and distribute rewards based on their contributions. We used a multi-index comprehensive evaluation to motivate workers to maintain high-quality and efficient participation in FL tasks. We conducted several simulations to evaluate the effectiveness of the semi-asynchronous mode, the reliability of the audit mechanism, and the contribution quantification strategy.
- 21 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 133394-133412
Open AccessA Blockchain-Based Auditable Semi-Asynchronous Federated Learning for Heterogeneous Clients
Federated learning (FL) is a privacy-preserving approach in Artificial Intelligence (AI) that involves exchanging intermediate training parameters instead of raw data, thereby avoiding privacy breaches and promoting effective data collaboration. However, FL still faces several unresolved challenges, including trust issues among participants because traditional FL lacks a mutual consensus auditing mechanism. Another challenge is that when the number of participating nodes is large and resources are heterogeneous; this can lead to low efficiency. To overcome these challenges, we propose a Blockchain-based Auditable Semi-Asynchronous Federated Learning (BASA-FL) system. BASA-FL includes a smart contract that coordinates and records the FL exchange process, enabling the ability to trace and audit the behavior of participating workers. In addition, we proposed an efficient semi-asynchronous approach in blockchain-based distributed FL as the main contribution to addressing heterogeneous problems. We designed a method to quantify worker contributions and distribute rewards based on their contributions. We used a multi-index comprehensive evaluation to motivate workers to maintain high-quality and efficient participation in FL tasks. We conducted several simulations to evaluate the effectiveness of the semi-asynchronous mode, the reliability of the audit mechanism, and the contribution quantification strategy.
- 3 June 2023
- Published by Springer Nature
- p. 431-437
BPFL: Blockchain-Enabled Distributed Edge Cluster for Personalized Federated Learning
- 3 June 2023
- Published by Springer Nature
- p. 431-437
BPFL: Blockchain-Enabled Distributed Edge Cluster for Personalized Federated Learning
- 3 June 2023
- Published by Springer Nature
- p. 423-429
A Blockchain-Based CCP Data Integrity Auditing Protocol for Smart HACCP
- 3 June 2023
- Published by Springer Nature
- p. 423-429
A Blockchain-Based CCP Data Integrity Auditing Protocol for Smart HACCP
- Open Access
- 5 April 2023
- Published by Frontiers Media SA in Frontiers in Public Health
- Vol. 11
Commentary: Integrated blockchain-deep learning approach for analyzing the electronic health records recommender system
Commentary: Integrated blockchain-deep learning approach for analyzing the electronic health records recommender system
- 5 April 2023
- Published by Frontiers Media SA in Frontiers in Public Health
- Vol. 11
Open AccessCommentary: Integrated blockchain-deep learning approach for analyzing the electronic health records recommender system
Commentary: Integrated blockchain-deep learning approach for analyzing the electronic health records recommender system
- Open Access
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 20 (6) , 10725-10740
Personalized federated learning for heterogeneous data: A distributed edge clustering approach
Federated learning (FL) is a distributed machine learning technique that allows multiple devices (e.g., smartphones and IoT devices) to collaborate in the training of a shared model with each device preserving the privacy of its local data. However, the highly heterogeneous distribution of data among clients in FL can result in poor convergence. In addressing this issue, the concept of personalized federated learning (PFL) has emerged. PFL aims to tackle the effects of non-independent and identically distributed data and statistical heterogeneity and to achieve personalized models with rapid model convergence. One approach is clustering-based PFL, which utilizes group-level client relationships to achieve personalization. However, this method still relies on a centralized approach, whereby the server coordinates all processes. To address these shortcomings, this study introduces a blockchain-enabled distributed edge cluster for PFL (BPFL) that combines the benefits of blockchain and edge computing. Blockchain technology can be used to enhance client privacy and security by recording transactions on immutable distributed ledger networks, thereby improving client selection and clustering. The edge computing system offers reliable storage and computation such that computational processing is locally performed in the edge infrastructure to be closer to clients. Thus, the real-time services and low-latency communication of PFL are improved. However, further work is required to develop a representative dataset for the examination of related types of attacks and defenses for a robust BPFL protocol.
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 20 (6) , 10725-10740
Open AccessPersonalized federated learning for heterogeneous data: A distributed edge clustering approach
Federated learning (FL) is a distributed machine learning technique that allows multiple devices (e.g., smartphones and IoT devices) to collaborate in the training of a shared model with each device preserving the privacy of its local data. However, the highly heterogeneous distribution of data among clients in FL can result in poor convergence. In addressing this issue, the concept of personalized federated learning (PFL) has emerged. PFL aims to tackle the effects of non-independent and identically distributed data and statistical heterogeneity and to achieve personalized models with rapid model convergence. One approach is clustering-based PFL, which utilizes group-level client relationships to achieve personalization. However, this method still relies on a centralized approach, whereby the server coordinates all processes. To address these shortcomings, this study introduces a blockchain-enabled distributed edge cluster for PFL (BPFL) that combines the benefits of blockchain and edge computing. Blockchain technology can be used to enhance client privacy and security by recording transactions on immutable distributed ledger networks, thereby improving client selection and clustering. The edge computing system offers reliable storage and computation such that computational processing is locally performed in the edge infrastructure to be closer to clients. Thus, the real-time services and low-latency communication of PFL are improved. However, further work is required to develop a representative dataset for the examination of related types of attacks and defenses for a robust BPFL protocol.
- Open Access
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
A Novel User Collusion‐Resistant Decentralized Multi‐Authority Attribute‐Based Encryption Scheme Using the Deposit on a Blockchain
Recently, the concept of a decentralized data marketplace is getting much attention to exchange user data. Multi‐authority attribute‐based encryption (ABE), which can provide flexibility and user‐centric access control, is previously widely used in decentralized data sharing applications and also becoming a foundation to build decentralized data trading applications. It is known that users in a multi‐authority ABE system can collude by sharing their secret information for malicious purposes. To address this issue, the collusion‐resistant multi‐authority ABE model was introduced in which a unique global identifier (GID) is issued by the central authority (CA) to each user. Unfortunately, such approach cannot be used directly to build a decentralized data marketplace as (a) such intervention of the CA is directly against the main motivation of the decentralized trading platform and, mostly importantly, (b) the CA can exploit its full knowledge on users’ GID to launch various attacks against users. Motivated by these observations, this paper introduces a novel user collusion‐resistant decentralized multi‐authority ABE scheme for privacy preserving data trading systems. In the existing multi‐authority ABE systems, users utilize his/her GID that is solely assigned by the CA to generate his/her secret keys throughout the collaboration with authorities and a user can compute multi‐authority keys by combining the secret keys (stem from the same GID) in various ways. In the proposed system, the CA only has a partial knowledge of users’ GIDs, and thus, users’ privacy can be protected. On the other hand, we set the user’s own partial GID as a secret which can be used to withdraw his/her deposit to discourage any possible collusion among users.
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Open AccessA Novel User Collusion‐Resistant Decentralized Multi‐Authority Attribute‐Based Encryption Scheme Using the Deposit on a Blockchain
Recently, the concept of a decentralized data marketplace is getting much attention to exchange user data. Multi‐authority attribute‐based encryption (ABE), which can provide flexibility and user‐centric access control, is previously widely used in decentralized data sharing applications and also becoming a foundation to build decentralized data trading applications. It is known that users in a multi‐authority ABE system can collude by sharing their secret information for malicious purposes. To address this issue, the collusion‐resistant multi‐authority ABE model was introduced in which a unique global identifier (GID) is issued by the central authority (CA) to each user. Unfortunately, such approach cannot be used directly to build a decentralized data marketplace as (a) such intervention of the CA is directly against the main motivation of the decentralized trading platform and, mostly importantly, (b) the CA can exploit its full knowledge on users’ GID to launch various attacks against users. Motivated by these observations, this paper introduces a novel user collusion‐resistant decentralized multi‐authority ABE scheme for privacy preserving data trading systems. In the existing multi‐authority ABE systems, users utilize his/her GID that is solely assigned by the CA to generate his/her secret keys throughout the collaboration with authorities and a user can compute multi‐authority keys by combining the secret keys (stem from the same GID) in various ways. In the proposed system, the CA only has a partial knowledge of users’ GIDs, and thus, users’ privacy can be protected. On the other hand, we set the user’s own partial GID as a secret which can be used to withdraw his/her deposit to discourage any possible collusion among users.
- Open Access
- 27 November 2020
- Published by Wiley in Security and Communication Networks
- Vol. 2020, 1-13
PyRos: A State Channel-Based Access Control System for a Public Blockchain Network
Blockchain is a technology that enables the implementation of a decentralized system by replacing the role of the centralized entity with the consensus of participants in the system to solve the problem of subordination to the centralized entity. Blockchain technology is being considered for application in numerous fields; however, the scalability limitation of a public blockchain has led many researchers to consider private blockchains, which reduce the security of the system while improving scalability. A state channel represents a leading approach among several scalability solutions, intended to address public blockchain scalability challenges while ensuring the security of the blockchain network. Participants in the channel perform the process of updating the state of the channel outside the blockchain. This process can proceed very quickly because it does not require the consensus of the blockchain network, but still, like on-chain, it can guarantee features such as irreversibility. In this paper, we propose the PyRos protocol, an access control system that supports the trading and sharing of data between individuals on a public blockchain based on the state channel. As far as we know, the research using the off-chain state channel for access control has not been proposed yet, so PyRos is a new approach in this field. In PyRos, user-defined access control policies are stored off-chain, and policy updates are always rapid regardless of the performance of the blockchain network. Moreover, PyRos provides means to prevent malicious participants from arbitrarily using the channel’s previous state while resolving constraints due to scalability problems, along with privacy guarantees for the transaction content. To evaluate the efficiency and security of PyRos, we provide qualitative analysis of security requirements and analysis in terms of the performance of public blockchain platforms.
- 27 November 2020
- Published by Wiley in Security and Communication Networks
- Vol. 2020, 1-13
Open AccessPyRos: A State Channel-Based Access Control System for a Public Blockchain Network
Blockchain is a technology that enables the implementation of a decentralized system by replacing the role of the centralized entity with the consensus of participants in the system to solve the problem of subordination to the centralized entity. Blockchain technology is being considered for application in numerous fields; however, the scalability limitation of a public blockchain has led many researchers to consider private blockchains, which reduce the security of the system while improving scalability. A state channel represents a leading approach among several scalability solutions, intended to address public blockchain scalability challenges while ensuring the security of the blockchain network. Participants in the channel perform the process of updating the state of the channel outside the blockchain. This process can proceed very quickly because it does not require the consensus of the blockchain network, but still, like on-chain, it can guarantee features such as irreversibility. In this paper, we propose the PyRos protocol, an access control system that supports the trading and sharing of data between individuals on a public blockchain based on the state channel. As far as we know, the research using the off-chain state channel for access control has not been proposed yet, so PyRos is a new approach in this field. In PyRos, user-defined access control policies are stored off-chain, and policy updates are always rapid regardless of the performance of the blockchain network. Moreover, PyRos provides means to prevent malicious participants from arbitrarily using the channel’s previous state while resolving constraints due to scalability problems, along with privacy guarantees for the transaction content. To evaluate the efficiency and security of PyRos, we provide qualitative analysis of security requirements and analysis in terms of the performance of public blockchain platforms.