Study on attacks against federated learning

Increasingly strict data privacy laws have seen many companies that are taking advantage of big data flock over from simple collaborative learning systems to federated learning systems which promise the reservation of data privacy. However, due to the collaborative and distributed nature of federate...

Full description

Saved in:
Bibliographic Details
Main Author: Wong, Yuan Neng
Other Authors: Yeo Chai Kiat
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/153157
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-153157
record_format dspace
spelling sg-ntu-dr.10356-1531572021-11-16T05:38:11Z Study on attacks against federated learning Wong, Yuan Neng Yeo Chai Kiat School of Computer Science and Engineering ASCKYEO@ntu.edu.sg Engineering::Computer science and engineering Increasingly strict data privacy laws have seen many companies that are taking advantage of big data flock over from simple collaborative learning systems to federated learning systems which promise the reservation of data privacy. However, due to the collaborative and distributed nature of federated learning, the resulting trained model will still be very exposed and vulnerable to many other kinds of attacks by malicious or compromised participants. In this project, we aim to study the various attack and defence methodologies that can be deployed in federated learning by implementing them using an existing open-sourced federated learning implementation as the base code. Such studies will allow us to understand the threats to the federated learning process and subsequently how to mitigate or even prevent any detrimental effects coming from the threat actors. The focus for this project will be on the distributed backdoor attack methodology and the PDGAN defence methodology. Bachelor of Engineering (Computer Science) 2021-11-09T11:42:10Z 2021-11-09T11:42:10Z 2021 Final Year Project (FYP) Wong, Y. N. (2021). Study on attacks against federated learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153157 https://hdl.handle.net/10356/153157 en SCSE20-0797 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
Wong, Yuan Neng
Study on attacks against federated learning
description Increasingly strict data privacy laws have seen many companies that are taking advantage of big data flock over from simple collaborative learning systems to federated learning systems which promise the reservation of data privacy. However, due to the collaborative and distributed nature of federated learning, the resulting trained model will still be very exposed and vulnerable to many other kinds of attacks by malicious or compromised participants. In this project, we aim to study the various attack and defence methodologies that can be deployed in federated learning by implementing them using an existing open-sourced federated learning implementation as the base code. Such studies will allow us to understand the threats to the federated learning process and subsequently how to mitigate or even prevent any detrimental effects coming from the threat actors. The focus for this project will be on the distributed backdoor attack methodology and the PDGAN defence methodology.
author2 Yeo Chai Kiat
author_facet Yeo Chai Kiat
Wong, Yuan Neng
format Final Year Project
author Wong, Yuan Neng
author_sort Wong, Yuan Neng
title Study on attacks against federated learning
title_short Study on attacks against federated learning
title_full Study on attacks against federated learning
title_fullStr Study on attacks against federated learning
title_full_unstemmed Study on attacks against federated learning
title_sort study on attacks against federated learning
publisher Nanyang Technological University
publishDate 2021
url https://hdl.handle.net/10356/153157
_version_ 1718368102026051584