Secure deep learning for distributed data against malicious central server.
In this paper, we propose a secure system for performing deep learning with distributed trainers connected to a central parameter server. Our system has the following two distinct features: (1) the distributed trainers can detect malicious activities in the server; (2) the distributed trainers can p...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0272423&type=printable |
| _version_ | 1826858946936176640 |
|---|---|
| author | Le Trieu Phong |
| author_facet | Le Trieu Phong |
| author_sort | Le Trieu Phong |
| collection | DOAJ |
| description | In this paper, we propose a secure system for performing deep learning with distributed trainers connected to a central parameter server. Our system has the following two distinct features: (1) the distributed trainers can detect malicious activities in the server; (2) the distributed trainers can perform both vertical and horizontal neural network training. In the experiments, we apply our system to medical data including magnetic resonance and X-ray images and obtain approximate or even better area-under-the-curve scores when compared to the existing scores. |
| first_indexed | 2024-04-11T11:56:32Z |
| format | Article |
| id | doaj.art-62c58d070e3a4524867ca5848cb46e5a |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2025-02-16T19:10:12Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-62c58d070e3a4524867ca5848cb46e5a2025-01-24T05:31:11ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01178e027242310.1371/journal.pone.0272423Secure deep learning for distributed data against malicious central server.Le Trieu PhongIn this paper, we propose a secure system for performing deep learning with distributed trainers connected to a central parameter server. Our system has the following two distinct features: (1) the distributed trainers can detect malicious activities in the server; (2) the distributed trainers can perform both vertical and horizontal neural network training. In the experiments, we apply our system to medical data including magnetic resonance and X-ray images and obtain approximate or even better area-under-the-curve scores when compared to the existing scores.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0272423&type=printable |
| spellingShingle | Le Trieu Phong Secure deep learning for distributed data against malicious central server. PLoS ONE |
| title | Secure deep learning for distributed data against malicious central server. |
| title_full | Secure deep learning for distributed data against malicious central server. |
| title_fullStr | Secure deep learning for distributed data against malicious central server. |
| title_full_unstemmed | Secure deep learning for distributed data against malicious central server. |
| title_short | Secure deep learning for distributed data against malicious central server. |
| title_sort | secure deep learning for distributed data against malicious central server |
| url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0272423&type=printable |
| work_keys_str_mv | AT letrieuphong securedeeplearningfordistributeddataagainstmaliciouscentralserver |