Reza, TanzimRahman, RafeedParvez, Mohammad ZavidEshan, M Sakib OsmanNafi, Md. Naimul HudaSakib, NazmusMaruf, Md. Ahnaf MorshedEmon, Mehedi Hasan2023-12-052023-12-0520232023-05ID 19101412ID 19101400ID 19101404ID 20101630ID 19301234http://hdl.handle.net/10361/21916Cataloged from PDF version of thesis.Includes bibliographical references (pages 48-50).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023.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 0.889.50 pagesenBrac 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.Computer visionFederated learningDeep learningHealthcareData poisoningRetinal OCTCognitive learning theoryArtificial intelligenceMachine learningFederated database systemsThesis