Enhancing Digital Image Forensics in Cybersecurity Using Machine Learning

Sawant, Hardik Sudhir (2023) Enhancing Digital Image Forensics in Cybersecurity Using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (446kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Digital image forensics is a crucial field that aims to authenticate and analyze digital images, considering the prevalence of advanced image editing software and techniques. This research paper delves into the potential of machine learning to enhance digital image forensics, specifically focusing on three machine learning models: Inception Net V3, Convolutional Neural Network (CNN), and Support Vector Machine (SVM).

The research methodology employed in this study is comprehensive, involving meticulous preprocessing of image data, careful selection and tuning of model hyperparameters, and rigorous evaluation of model performance. The models are trained and tested on a dataset of images, and their accuracy in classifying these images serves as the basis for their performance evaluation.

The results obtained from the experiments uncover notable disparities in the performance of the three models. Both the Inception Net V3 and SVM models exhibit superior performance, achieving an accuracy rate of 75% in classifying images. Conversely, the CNN model lags behind significantly, attaining a mere 25% accuracy. These findings highlight the potential of machine learning, particularly the Inception Net V3 and SVM models, in bolstering digital image forensics.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jayasekera, Evgeniia UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Tamara Malone
Date Deposited:	05 Nov 2024 15:14
Last Modified:	05 Nov 2024 15:14
URI:	https://norma.ncirl.ie/id/eprint/7148

Actions (login required)

View Item