Browsing by Author "Emon, Mehedi Hasan"

Now showing 1 - 2 of 2

A secured federated learning system leveraging confidence score to identify retinal disease
(BRAC University, 2023-05) Eshan, M Sakib Osman; Nafi, Md. Naimul Huda; Sakib, Nazmus; Maruf, Md. Ahnaf Morshed; Emon, Mehedi Hasan; Reza, Tanzim; Rahman, Rafeed; Parvez, Mohammad Zavid
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.
Authentication Method for Password Encryption
(Daffodil International University, 2019-12) Rahman, Md. Khalidur; Roy, Sovan; Emon, Mehedi Hasan
This the 21st century where each and everything are becoming digitalized. Everyone makes his life comfortable with the benefits of technology. As a result various kinds of data like personal, business and so on are stored in the online platform. To access the data the users need to create account and have to use password in the system to get authenticated. Sometimes the sensitive information like password of a user has stolen from the database by the hacker. Without using the traditional method we design a methodology named “AUTHENTICATION METHOD FOR PASSWORD ENCRYPTION” to encrypt the password of the user. In our methodology we make a conversion of user inputted password and date of birth during the time of registration. According to the methodology which we design, a calculation will happen and finally the output result will save into the database against password without saving the raw password. When the user login to the system and input his raw password then according to the methodology it will calculate again and match the calculated value with the database value. If the database access goes to any third party, they will not get the exact password of any users. Our encryption method secure the users password into database as well as secure them to leak their personal sensitive data.