Deepfake Detection using Bayesian Neural Networks

Joshi, Parag Suresh (2022) Deepfake Detection using Bayesian Neural Networks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (852kB) | Preview

Abstract

Deepfakes are images or videos that are manufactured by using artificial algorithms, image processing, and face swapping. Deepfakes, which use artificial intelligence (AI) to represent someone speaking or doing things that did not take place, have the potential to have a significant negative impact on society. The study reviews known deep learning approaches for Deepfake detection and seeks to present an additional way for Deepfake video identification using Bayesian Neural Networks. Deep learning is constantly advancing in terms of both producing and identifying deepfakes. A deepfake detection model built with an earlier dataset may become obsolete over time, necessitating the development of a new detection approach. Results of the research indicate that the model provides an average performance with an accuracy of 58 percent on an untrained dataset.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TR Photography Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	20 Feb 2023 13:50
Last Modified:	02 Mar 2023 11:51
URI:	https://norma.ncirl.ie/id/eprint/6195

Actions (login required)

View Item