Deep Learning Technology for Face Forgery Detection: A Survey

TL;DR

This survey reviews recent deep learning methods for detecting deepfake facial images and videos, highlighting advances, challenges, and future directions to improve detection accuracy and robustness.

Contribution

It provides a comprehensive overview of deepfake generation techniques, datasets, detection methods, and discusses current challenges and future research directions.

Findings

Deepfake detection methods vary in effectiveness and generalization.

Current datasets have limitations affecting detection performance.

Future research should focus on improving robustness and dataset diversity.

Abstract

Currently, the rapid development of computer vision and deep learning has enabled the creation or manipulation of high-fidelity facial images and videos via deep generative approaches. This technology, also known as deepfake, has achieved dramatic progress and become increasingly popular in social media. However, the technology can generate threats to personal privacy and national security by spreading misinformation. To diminish the risks of deepfake, it is desirable to develop powerful forgery detection methods to distinguish fake faces from real faces. This paper presents a comprehensive survey of recent deep learning-based approaches for facial forgery detection. We attempt to provide the reader with a deeper understanding of the current advances as well as the major challenges for deepfake detection based on deep learning. We present an overview of deepfake techniques and analyse the characteristics of various deepfake datasets. We then provide a systematic review of different categories of deepfake detection and state-of-the-art deepfake detection methods. The drawbacks of existing detection methods are analyzed, and future research directions are discussed to address the challenges in improving both the performance and generalization of deepfake detection.