Author(s)

Majed M. Alwateer

Department of Computer Science, College of Computer Science and Engineering, Taibah University, Yanbu, Saudi Arabia.

Deep learning is a practical and efficient technique that has been used extensively in many domains. Using deep learning technology, deepfakes create fake images of a person that people cannot distinguish from the real one. Recently, many researchers have focused on understanding how deepkakes work and detecting using deep learning approaches. This paper introduces an explainable deepfake framework for images creation and classification. The framework consists of three main parts: the first approach is called Instant ID which is used to create deepfacke images from the original one; the second approach called Xception classifies the real and deepfake images; the third approach called Local Interpretable Model (LIME) provides a method for interpreting the predictions of any machine learning model in a local and interpretable manner. Our study proposes deepfake approach that achieves 100% precision and 100% accuracy for deepfake creation and classification. Furthermore, the results highlight the superior performance of the proposed model in deep fake creation and classification.

Deepfakes, Machine Learning, Deep Learning Fake Detection, Social Media LIME Technique

Alwateer, M. (2024) Explainable Deep Fake Framework for Images Creation and Classification. Journal of Computer and Communications, 12, 86-101. doi: 10.4236/jcc.2024.125006.