•  
  •  
 

Abstract

In recent years, Advancements in Artificial Intelligence (AI), particularly deep learning (DL), have made great strides in the creation of highly realistic deepfakes, which manipulate facial forensics to generate convincing fake faces or expressions. These manipulations pose significant threats to individual privacy and the integrity of legal, political, and social institutions. In fact, several existing studies have recently pursued the development of machine learning techniques for detecting deepfake content, with the overarching aim of protecting the victim's privacy or curbing the rise of picture fabrication. Despite extensive research on DL-based deepfake detection systems, challenges such as detecting facial swaps under occlusion or subtle alteration remain insufficiently addressed. This study provides a comprehensive detailed evaluation of state-of the art DL approaches for detecting such manipulations, focusing on their strengths and limitations. Additionally, it reviews recent deepfake datasets (2019 to date) to identify their adequacy for adequacy for training and testing these models. By addressing the gaps and limitations in current existing methods and datasets, this study aims to pave the way for redefining DL-based detection techniques tailored to facial-swap-based deepfakes. It aspires to enhance the integrity and reliability of image media and contributes to the ongoing effort to mitigate the risk posed by advanced image manipulation.

Download

Share

COinS