A trustworthy BCFL in indoor localization system
To achieve an exact indoor localization effect, the fingerprinting-based machine learning method is a promising choice. But in the process of training arise some privacy and security concerns. To handle the privacy concern, the common choice is adopting a federated learning (FL) framework. However t...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/180287 |
| _version_ | 1826122236857155584 |
|---|---|
| author | Wang, Junfei |
| author2 | Xie Lihua |
| author_facet | Xie Lihua Wang, Junfei |
| author_sort | Wang, Junfei |
| collection | NTU |
| description | To achieve an exact indoor localization effect, the fingerprinting-based machine learning method is a promising choice. But in the process of training arise some privacy and security concerns. To handle the privacy concern, the common choice is adopting a federated learning (FL) framework. However traditional FL frameworks are helpless against remaining security concerns, such as malicious attacks and single-point failure.
To solve these concerns, we design a trustworthy Blockchain-based federated learning (BCFL) framework called DFLoc. Specifically, the central server in traditional federated learning is replaced with a PoS blockchain, to solve the single-point failure. Malicious attacks are figured out by the elaborated DFLoc Validator Mechanism.
To evaluate the performance of our proposed framework in detail, we conduct extensive experiments using a real-world dataset of fingerprinting-based indoor localization called UJIIndoorLoc. The experiment results demonstrate that our DFLoc can effectively mitigate the challenges of malicious attacks and singlepoint failure in a 3D environment when compared with the traditional centralized FL systems. |
| first_indexed | 2025-03-09T13:11:15Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/180287 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-03-09T13:11:15Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1802872024-10-04T15:43:45Z A trustworthy BCFL in indoor localization system Wang, Junfei Xie Lihua School of Electrical and Electronic Engineering ELHXIE@ntu.edu.sg Engineering Federated learning Blockchain Indoor localization Single-point failure Malicious attack To achieve an exact indoor localization effect, the fingerprinting-based machine learning method is a promising choice. But in the process of training arise some privacy and security concerns. To handle the privacy concern, the common choice is adopting a federated learning (FL) framework. However traditional FL frameworks are helpless against remaining security concerns, such as malicious attacks and single-point failure. To solve these concerns, we design a trustworthy Blockchain-based federated learning (BCFL) framework called DFLoc. Specifically, the central server in traditional federated learning is replaced with a PoS blockchain, to solve the single-point failure. Malicious attacks are figured out by the elaborated DFLoc Validator Mechanism. To evaluate the performance of our proposed framework in detail, we conduct extensive experiments using a real-world dataset of fingerprinting-based indoor localization called UJIIndoorLoc. The experiment results demonstrate that our DFLoc can effectively mitigate the challenges of malicious attacks and singlepoint failure in a 3D environment when compared with the traditional centralized FL systems. Master's degree 2024-09-30T12:19:18Z 2024-09-30T12:19:18Z 2024 Thesis-Master by Coursework Wang, J. (2024). A trustworthy BCFL in indoor localization system. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/180287 https://hdl.handle.net/10356/180287 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering Federated learning Blockchain Indoor localization Single-point failure Malicious attack Wang, Junfei A trustworthy BCFL in indoor localization system |
| title | A trustworthy BCFL in indoor localization system |
| title_full | A trustworthy BCFL in indoor localization system |
| title_fullStr | A trustworthy BCFL in indoor localization system |
| title_full_unstemmed | A trustworthy BCFL in indoor localization system |
| title_short | A trustworthy BCFL in indoor localization system |
| title_sort | trustworthy bcfl in indoor localization system |
| topic | Engineering Federated learning Blockchain Indoor localization Single-point failure Malicious attack |
| url | https://hdl.handle.net/10356/180287 |
| work_keys_str_mv | AT wangjunfei atrustworthybcflinindoorlocalizationsystem AT wangjunfei trustworthybcflinindoorlocalizationsystem |