A secured federated learning system leveraging confidence score to identify retinal disease

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023.

Detalhes bibliográficos
Principais autores:	Eshan, M Sakib Osman, Nafi, Md. Naimul Huda, Sakib, Nazmus, Maruf, Md. Ahnaf Morshed, Emon, Mehedi Hasan
Outros Autores:	Reza, Tanzim
Formato:	Tese
Idioma:	English
Publicado em:	Brac University 2023
Assuntos:	Computer vision Federated learning Deep learning Healthcare Data poisoning Retinal OCT Cognitive learning theory Artificial intelligence Machine learning Federated database systems
Acesso em linha:	http://hdl.handle.net/10361/21916

id	10361-21916
record_format	dspace
spelling	10361-219162023-12-05T21:02:29Z A secured federated learning system leveraging confidence score to identify retinal disease Eshan, M Sakib Osman Nafi, Md. Naimul Huda Sakib, Nazmus Maruf, Md. Ahnaf Morshed Emon, Mehedi Hasan Reza, Tanzim Rahman, Rafeed Parvez, Mohammad Zavid Department of Computer Science and Engineering, Brac University Computer vision Federated learning Deep learning Healthcare Data poisoning Retinal OCT Cognitive learning theory Artificial intelligence Machine learning Federated database systems This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023. Cataloged from PDF version of thesis. Includes bibliographical references (pages 48-50). Federated learning is a distributed machine learning paradigm that enables multiple clients to collaboratively train a global model without sharing their local data. How- ever, federated learning is vulnerable to adversarial attacks, where malicious clients can manipulate their local updates to degrade the performance or compromise the privacy of the global model. To mitigate this problem, this paper proposes a novel method that reduces the influence of malicious clients based on their confidence. We conducted our experiments on the Retinal OCT dataset. The proposed technique significantly improves the global model’s precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC-ROC). Precision rises from 0.869 to 0.906, recall rises from 0.836 to 0.889, F1 score rises from 0.852 to 0.898, and AUC-ROC rises from 0.836 to 0.889. M Sakib Osman Eshan Md. Naimul Huda Nafi Nazmus Sakib Md. Ahnaf Morshed Maruf Mehedi Hasan Emon B.Sc. in Computer Science and Engineering 2023-12-05T06:03:10Z 2023-12-05T06:03:10Z 2023 2023-05 Thesis ID 19101412 ID 19101400 ID 19101404 ID 20101630 ID 19301234 http://hdl.handle.net/10361/21916 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 50 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Computer vision Federated learning Deep learning Healthcare Data poisoning Retinal OCT Cognitive learning theory Artificial intelligence Machine learning Federated database systems
spellingShingle	Computer vision Federated learning Deep learning Healthcare Data poisoning Retinal OCT Cognitive learning theory Artificial intelligence Machine learning Federated database systems Eshan, M Sakib Osman Nafi, Md. Naimul Huda Sakib, Nazmus Maruf, Md. Ahnaf Morshed Emon, Mehedi Hasan A secured federated learning system leveraging confidence score to identify retinal disease
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023.
author2	Reza, Tanzim
author_facet	Reza, Tanzim Eshan, M Sakib Osman Nafi, Md. Naimul Huda Sakib, Nazmus Maruf, Md. Ahnaf Morshed Emon, Mehedi Hasan
format	Thesis
author	Eshan, M Sakib Osman Nafi, Md. Naimul Huda Sakib, Nazmus Maruf, Md. Ahnaf Morshed Emon, Mehedi Hasan
author_sort	Eshan, M Sakib Osman
title	A secured federated learning system leveraging confidence score to identify retinal disease
title_short	A secured federated learning system leveraging confidence score to identify retinal disease
title_full	A secured federated learning system leveraging confidence score to identify retinal disease
title_fullStr	A secured federated learning system leveraging confidence score to identify retinal disease
title_full_unstemmed	A secured federated learning system leveraging confidence score to identify retinal disease
title_sort	secured federated learning system leveraging confidence score to identify retinal disease
publisher	Brac University
publishDate	2023
url	http://hdl.handle.net/10361/21916
work_keys_str_mv	AT eshanmsakibosman asecuredfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT nafimdnaimulhuda asecuredfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT sakibnazmus asecuredfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT marufmdahnafmorshed asecuredfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT emonmehedihasan asecuredfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT eshanmsakibosman securedfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT nafimdnaimulhuda securedfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT sakibnazmus securedfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT marufmdahnafmorshed securedfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease AT emonmehedihasan securedfederatedlearningsystemleveragingconfidencescoretoidentifyretinaldisease
_version_	1814307015160233984

A secured federated learning system leveraging confidence score to identify retinal disease

Registros relacionados