ST-BFL: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain Framework
Federated Learning (FL) relies on on-device training to avoid the migration of devices’ data to a centralized server to address privacy leakage. Moreover, FL is feasible for scenarios (e.g., autonomous cars) where an enormous amount of data is generated every day. Transferring only local...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9617624/ |
| _version_ | 1818840077172736000 |
|---|---|
| author | Umer Majeed Latif U. Khan Abdullah Yousafzai Zhu Han Bang Ju Park Choong Seon Hong |
| author_facet | Umer Majeed Latif U. Khan Abdullah Yousafzai Zhu Han Bang Ju Park Choong Seon Hong |
| author_sort | Umer Majeed |
| collection | DOAJ |
| description | Federated Learning (FL) relies on on-device training to avoid the migration of devices’ data to a centralized server to address privacy leakage. Moreover, FL is feasible for scenarios (e.g., autonomous cars) where an enormous amount of data is generated every day. Transferring only local model updates in the case of FL is highly communication-efficient compared to transferring all data in the case of centralized machine learning (ML). Although FL offers many advantages, it also has some challenges. A malicious aggregation server can infer device information via local model updates. Another downside of FL is the centralized aggregation server that can malfunction due to an attack or physical damage. To address these issues, we propose a novel Structured Transparency empowered cross-silo Federated Learning on the Blockchain (ST-BFL) framework. In ST-BFL, homomorphic encryption, FL-aggregators, FL-verifiers, and smart contract are employed, which satisfy various structured transparency components, such as input privacy, output privacy, output verification, and flow governance. We present the framework architecture, algorithms, and sequence diagram of our ST-BFL framework to show how different entities interact in ST-BFL for the FL process. We also present a simplified class diagram of ST-BFL’s smart contract for an FL task. Finally, we perform a simulation to analyze our framework from the perspective of aggregation time, accuracy, and storage size. The qualitative and quantitative evaluation shows that ST-BFL has the same accuracy as traditional FL. However, ST-BFL provides input privacy, output privacy, input verification, output verification, and flow governance at the expense of relatively higher computation and communication costs than traditional FL. |
| first_indexed | 2024-12-19T04:04:27Z |
| format | Article |
| id | doaj.art-46f427ed361841c381889c306c59b45a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T04:04:27Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-46f427ed361841c381889c306c59b45a2022-12-21T20:36:34ZengIEEEIEEE Access2169-35362021-01-01915563415565010.1109/ACCESS.2021.31286229617624ST-BFL: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain FrameworkUmer Majeed0https://orcid.org/0000-0002-5908-3889Latif U. Khan1https://orcid.org/0000-0002-7678-6949Abdullah Yousafzai2https://orcid.org/0000-0001-6360-0802Zhu Han3https://orcid.org/0000-0002-6606-5822Bang Ju Park4https://orcid.org/0000-0002-7078-7182Choong Seon Hong5https://orcid.org/0000-0003-3484-7333Department of Computer Science and Engineering, Kyung Hee University, Yongin, South KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Yongin, South KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Yongin, South KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Yongin, South KoreaDepartment of Electronic Engineering, Gachon University, Seongnam, South KoreaDepartment of Computer Science and Engineering, Kyung Hee University, Yongin, South KoreaFederated Learning (FL) relies on on-device training to avoid the migration of devices’ data to a centralized server to address privacy leakage. Moreover, FL is feasible for scenarios (e.g., autonomous cars) where an enormous amount of data is generated every day. Transferring only local model updates in the case of FL is highly communication-efficient compared to transferring all data in the case of centralized machine learning (ML). Although FL offers many advantages, it also has some challenges. A malicious aggregation server can infer device information via local model updates. Another downside of FL is the centralized aggregation server that can malfunction due to an attack or physical damage. To address these issues, we propose a novel Structured Transparency empowered cross-silo Federated Learning on the Blockchain (ST-BFL) framework. In ST-BFL, homomorphic encryption, FL-aggregators, FL-verifiers, and smart contract are employed, which satisfy various structured transparency components, such as input privacy, output privacy, output verification, and flow governance. We present the framework architecture, algorithms, and sequence diagram of our ST-BFL framework to show how different entities interact in ST-BFL for the FL process. We also present a simplified class diagram of ST-BFL’s smart contract for an FL task. Finally, we perform a simulation to analyze our framework from the perspective of aggregation time, accuracy, and storage size. The qualitative and quantitative evaluation shows that ST-BFL has the same accuracy as traditional FL. However, ST-BFL provides input privacy, output privacy, input verification, output verification, and flow governance at the expense of relatively higher computation and communication costs than traditional FL.https://ieeexplore.ieee.org/document/9617624/BlockchainEthereumfederated learningflow governancehomomorphic encryptioninput privacy |
| spellingShingle | Umer Majeed Latif U. Khan Abdullah Yousafzai Zhu Han Bang Ju Park Choong Seon Hong ST-BFL: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain Framework IEEE Access Blockchain Ethereum federated learning flow governance homomorphic encryption input privacy |
| title | ST-BFL: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain Framework |
| title_full | ST-BFL: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain Framework |
| title_fullStr | ST-BFL: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain Framework |
| title_full_unstemmed | ST-BFL: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain Framework |
| title_short | ST-BFL: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain Framework |
| title_sort | st bfl a structured transparency empowered cross silo federated learning on the blockchain framework |
| topic | Blockchain Ethereum federated learning flow governance homomorphic encryption input privacy |
| url | https://ieeexplore.ieee.org/document/9617624/ |
| work_keys_str_mv | AT umermajeed stbflastructuredtransparencyempoweredcrosssilofederatedlearningontheblockchainframework AT latifukhan stbflastructuredtransparencyempoweredcrosssilofederatedlearningontheblockchainframework AT abdullahyousafzai stbflastructuredtransparencyempoweredcrosssilofederatedlearningontheblockchainframework AT zhuhan stbflastructuredtransparencyempoweredcrosssilofederatedlearningontheblockchainframework AT bangjupark stbflastructuredtransparencyempoweredcrosssilofederatedlearningontheblockchainframework AT choongseonhong stbflastructuredtransparencyempoweredcrosssilofederatedlearningontheblockchainframework |