CIFAKE: image classification and explainable identification of AI-generated synthetic images

Bird, J.J. ORCID: 0000-0002-9858-1231 and Lotfi, A. ORCID: 0000-0002-5139-6565, 2024. CIFAKE: image classification and explainable identification of AI-generated synthetic images. IEEE Access. ISSN 2169-3536

Full text not available from this repository.

Abstract

Recent advances in synthetic data have enabled the generation of images with such high quality that human beings cannot tell the difference between real-life photographs and Artificial Intelligence (AI) generated images. Given the critical necessity of data reliability and authentication, this article proposes to enhance our ability to recognise AI-generated images through computer vision. Initially, a synthetic dataset is generated that mirrors the ten classes of the already available CIFAR-10 dataset with latent diffusion, providing a contrasting set of images for comparison to real photographs. The model is capable of generating complex visual attributes, such as photorealistic reflections in water. The two sets of data present as a binary classification problem with regard to whether the photograph is real or generated by AI. This study then proposes the use of a Convolutional Neural Network (CNN) to classify the images into two categories; Real or Fake. Following hyperparameter tuning and the training of 36 individual network topologies, the optimal approach could correctly classify the images with 92.98% accuracy. Finally, this study implements explainable AI via Gradient Class Activation Mapping to explore which features within the images are useful for classification. Interpretation reveals interesting concepts within the image, in particular, noting that the actual entity itself does not hold useful information for classification; instead, the model focuses on small visual imperfections in the background of the images. The complete dataset engineered for this study, referred to as the CIFAKE dataset, is made publicly available to the research community for future work.

Item Type:	Journal article
Publication Title:	IEEE Access
Creators:	Bird, J.J. and Lotfi, A.
Publisher:	Institute of Electrical and Electronics Engineers
Date:	19 January 2024
ISSN:	2169-3536
Identifiers:	Number Type 10.1109/access.2024.3356122 DOI 1855215 Other
Rights:	This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0
Divisions:	Schools > School of Science and Technology
Record created by:	Jonathan Gallacher
Date Added:	29 Jan 2024 11:07
Last Modified:	29 Jan 2024 11:07
URI:	https://irep.ntu.ac.uk/id/eprint/50758

Actions (login required)

Edit View

Views

Downloads