Differential privacy in peer-to-peer federated learning
Neural networks have become tremendously successful in recent times due to larger computing power and availability of tagged datasets for various applications. Training these networks is computationally demanding and often requires proprietary datasets to yield usable insights. In order to incent...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/165929 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-165929 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1659292023-04-21T15:37:02Z Differential privacy in peer-to-peer federated learning Rajkumar, Snehaa Anupam Chattopadhyay School of Computer Science and Engineering anupam@ntu.edu.sg Engineering::Computer science and engineering Neural networks have become tremendously successful in recent times due to larger computing power and availability of tagged datasets for various applications. Training these networks is computationally demanding and often requires proprietary datasets to yield usable insights. In order to incentivise stakeholders to share their datasets in order to build stronger neural networks and protect their privacy interests, it is important to implement differential privacy mechanisms during the training of neural networks to protect against attacks that might expose their data to malicious agents. The objective of this project is to study the effectiveness of differential privacy implementation on peer-to-peer federated learning in protecting proprietary data from exposure. Bachelor of Engineering (Computer Science) 2023-04-17T02:12:39Z 2023-04-17T02:12:39Z 2023 Final Year Project (FYP) Rajkumar, S. (2023). Differential privacy in peer-to-peer federated learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/165929 https://hdl.handle.net/10356/165929 en SCSE22-0022 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering |
spellingShingle |
Engineering::Computer science and engineering Rajkumar, Snehaa Differential privacy in peer-to-peer federated learning |
description |
Neural networks have become tremendously successful in recent times due to larger
computing power and availability of tagged datasets for various applications. Training
these networks is computationally demanding and often requires proprietary datasets to
yield usable insights. In order to incentivise stakeholders to share their datasets in order
to build stronger neural networks and protect their privacy interests, it is important to
implement differential privacy mechanisms during the training of neural networks to
protect against attacks that might expose their data to malicious agents. The objective
of this project is to study the effectiveness of differential privacy implementation on
peer-to-peer federated learning in protecting proprietary data from exposure. |
author2 |
Anupam Chattopadhyay |
author_facet |
Anupam Chattopadhyay Rajkumar, Snehaa |
format |
Final Year Project |
author |
Rajkumar, Snehaa |
author_sort |
Rajkumar, Snehaa |
title |
Differential privacy in peer-to-peer federated learning |
title_short |
Differential privacy in peer-to-peer federated learning |
title_full |
Differential privacy in peer-to-peer federated learning |
title_fullStr |
Differential privacy in peer-to-peer federated learning |
title_full_unstemmed |
Differential privacy in peer-to-peer federated learning |
title_sort |
differential privacy in peer-to-peer federated learning |
publisher |
Nanyang Technological University |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/165929 |
_version_ |
1764208052249034752 |