An explainable deepfake detection framework on a novel unconstrained dataset

Abstract In this work, we created a new large-scale unconstrained high-quality Deepfake Image (DFIM-HQ) dataset containing 140K images. Compared to existing datasets, this dataset includes a variety of diverse scenarios, pose variations, high-quality degradations, and illumination variations, making...

Full description

Bibliographic Details

Published in:	Complex & Intelligent Systems
Main Authors:	Sherin Mathews, Shivangee Trivedi, Amanda House, Steve Povolny, Celeste Fralick
Format:	Article
Language:	English
Published:	Springer 2023-01-01
Subjects:	Deepfakes Deepfake image detection techniques Digital media forensics Deep learning Explainability AI bias
Online Access:	https://doi.org/10.1007/s40747-022-00956-7