Deep Learning for Deepfakes Creation and Detection: A Survey

TL;DR

This survey reviews deepfake creation and detection algorithms, discussing challenges, trends, and future directions to improve robustness against increasingly sophisticated deepfake technologies.

Contribution

It provides a comprehensive overview of existing deepfake generation and detection methods, highlighting research gaps and proposing directions for future research.

Findings

Deepfake detection methods vary widely in effectiveness.

Current challenges include high-quality fake generation and robust detection.

Research trends focus on deep learning and multimodal approaches.

Abstract

Deep learning has been successfully applied to solve various complex problems ranging from big data analytics to computer vision and human-level control. Deep learning advances however have also been employed to create software that can cause threats to privacy, democracy and national security. One of those deep learning-powered applications recently emerged is deepfake. Deepfake algorithms can create fake images and videos that humans cannot distinguish them from authentic ones. The proposal of technologies that can automatically detect and assess the integrity of digital visual media is therefore indispensable. This paper presents a survey of algorithms used to create deepfakes and, more importantly, methods proposed to detect deepfakes in the literature to date. We present extensive discussions on challenges, research trends and directions related to deepfake technologies. By reviewing the background of deepfakes and state-of-the-art deepfake detection methods, this study provides a comprehensive overview of deepfake techniques and facilitates the development of new and more robust methods to deal with the increasingly challenging deepfakes.