Deepfake Detection Research Project

Singh, Harshpreet (2020) Deepfake Detection Research Project. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (321kB) | Preview

Abstract

With the recent developments on the creation of deepfake videos using Generative Adversarial Network (GAN), which can produce realistic photos and videos, the reliability of digital images is becoming more challenging to identify. This research is an approach to develop a deep learning model which can efficiently distinguish between a deepfake and a real video. Research work on transfer learning of computer vision to use the previously build features of the neural network of image categorization and build a new model over it. Deep learning is continuously evolving a lot in both areas of generating and detecting deepfakes. A model developed for detection of deepfake designed with older dataset may expire in time, and a need for new detection technique will always be there. Result of the research is auspicious with more than 90% accuracy and the area of evolvement and advancement.

Item Type:	Thesis (Masters)
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 T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	25 Jan 2021 15:32
Last Modified:	25 Jan 2021 15:32
URI:	https://norma.ncirl.ie/id/eprint/4473

Actions (login required)

View Item