Homomorphic encryption(HE) enabled federated learning
In this report, to maximise data privacy, we conducted Federated Learning algorithm with Homomorphic Encryption. The project was done in stages. Initially, federated learning was done without applying homomorphic encryption. Homomorphic encryption was applied in a progressive manner at a later stage...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/138191 |
| _version_ | 1826127380434911232 |
|---|---|
| author | Myat Nyein Soe |
| author2 | Anupam Chattopadhyay |
| author_facet | Anupam Chattopadhyay Myat Nyein Soe |
| author_sort | Myat Nyein Soe |
| collection | NTU |
| description | In this report, to maximise data privacy, we conducted Federated Learning algorithm with Homomorphic Encryption. The project was done in stages. Initially, federated learning was done without applying homomorphic encryption. Homomorphic encryption was applied in a progressive manner at a later stage and its performance was thoroughly studied. Additionally, the existing projects incorporating homomorphic encryption was studied to further improve our project. Various parameters pertaining to homomorphic encryption were also explored to observe the key features and necessary trade-offs. Based on the testing results, it was discovered that the prediction accuracy was relatively higher for the ML models generated from the averaged weights within the federated network. For future work, different datasets will be used to further confirm this finding. |
| first_indexed | 2024-10-01T07:07:56Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/138191 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:07:56Z |
| publishDate | 2020 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1381912020-04-28T06:07:13Z Homomorphic encryption(HE) enabled federated learning Myat Nyein Soe Anupam Chattopadhyay School of Computer Science and Engineering anupam@ntu.edu.sg Engineering::Computer science and engineering::Data::Data encryption In this report, to maximise data privacy, we conducted Federated Learning algorithm with Homomorphic Encryption. The project was done in stages. Initially, federated learning was done without applying homomorphic encryption. Homomorphic encryption was applied in a progressive manner at a later stage and its performance was thoroughly studied. Additionally, the existing projects incorporating homomorphic encryption was studied to further improve our project. Various parameters pertaining to homomorphic encryption were also explored to observe the key features and necessary trade-offs. Based on the testing results, it was discovered that the prediction accuracy was relatively higher for the ML models generated from the averaged weights within the federated network. For future work, different datasets will be used to further confirm this finding. Bachelor of Engineering (Computer Science) 2020-04-28T06:07:12Z 2020-04-28T06:07:12Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/138191 en SCSE19-0303 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Data::Data encryption Myat Nyein Soe Homomorphic encryption(HE) enabled federated learning |
| title | Homomorphic encryption(HE) enabled federated learning |
| title_full | Homomorphic encryption(HE) enabled federated learning |
| title_fullStr | Homomorphic encryption(HE) enabled federated learning |
| title_full_unstemmed | Homomorphic encryption(HE) enabled federated learning |
| title_short | Homomorphic encryption(HE) enabled federated learning |
| title_sort | homomorphic encryption he enabled federated learning |
| topic | Engineering::Computer science and engineering::Data::Data encryption |
| url | https://hdl.handle.net/10356/138191 |
| work_keys_str_mv | AT myatnyeinsoe homomorphicencryptionheenabledfederatedlearning |