TARU PUBLICATIONS
Author

Shankar M. Patil

Department of Artificial Intelligence and Data Science, Ghansoli, Smt. Indira Gandhi College of Engineering, Navi Mumbai, Maharashtra, 400701, India

Published papers
3
Citations
0
Views
731
Downloads
262

Publications

3 papers
Open Access Research Article·pp. 655–662·Vol. 29, Issue 2-AFeb 2026

Exploring facial biometrics in multi-factor authentication systems for secure banking applications

Mandeep Kaur, Mayank Kumar Goyal, Durga Prasad Yadav, Shankar M. Patil, Malayaj Kumar, Mohammed Eltahir Abdelhag

Published Online: 07 Feb 2026DOI: 10.47974/JDMSC-2508

In this paper: Due to convenience, as well as its security, facial recognition is fast becoming an important component of multi-factor authentication (MFA) for biometric authentication, especially banking. So, while...

AbstractReferencesFull Text PDF (339 KB)Views: 246Downloads: 97Citations: 0
Open Access Research Article·pp. 1141–1151·Vol. 46, Issue 4-BMay 2025

A framework for multi-task learning optimization in deep neural networks : Balancing task priorities for improved performance

Ravindra K. Moje, Bhavana Tiple, Shankar M. Patil, Tushar Jadhav, Aniket Prakashrao Munshi, Akshay Revekar

Published Online: 31 May 2025DOI: 10.47974/JIOS-1898

In this paper: Deep neural networks (DNNs) have made multi-task learning (MTL) a powerful way to learn multiple linked tasks at once, using shared models to improve generalization and speed. But successfully matchin...

AbstractReferencesFull Text PDF (819 KB)Views: 200Downloads: 76Citations: 0
Open Access Research Article·pp. 1153–1163·Vol. 46, Issue 4-BMay 2025

Adaptive noise injection techniques for optimizing deep learning models under adversarial attacks

Araddhana Arvind Deshmukh, Priyanka S. Dhumal, Shankar M. Patil, Samir N. Ajani, Gaurav Gondhalekar, Ajay Kumar Mehta, Saurabh Bhattacharya

Published Online: 31 May 2025DOI: 10.47974/JIOS-1899

In this paper: More and more apps are using deep learning models, which has raised worries about how vulnerable they are to threats from other programs. As a result, academics have looked into adaptable noise input...

AbstractReferencesFull Text PDF (695 KB)Views: 285Downloads: 89Citations: 0