DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection

TL;DR

This survey reviews face manipulation techniques, especially DeepFakes, and discusses detection methods, datasets, benchmarks, and future challenges in identifying realistic fake face content created by advanced deep learning models.

Contribution

It provides a comprehensive overview of face manipulation methods, detection techniques, and benchmarks, highlighting recent DeepFake advancements and open issues in the field.

Findings

DeepFake techniques have become more realistic and challenging to detect.

Existing datasets and benchmarks are crucial for evaluating fake detection methods.

Open issues include improving detection accuracy and addressing ethical concerns.

Abstract

The free access to large-scale public databases, together with the fast progress of deep learning techniques, in particular Generative Adversarial Networks, have led to the generation of very realistic fake content with its corresponding implications towards society in this era of fake news. This survey provides a thorough review of techniques for manipulating face images including DeepFake methods, and methods to detect such manipulations. In particular, four types of facial manipulation are reviewed: i) entire face synthesis, ii) identity swap (DeepFakes), iii) attribute manipulation, and iv) expression swap. For each manipulation group, we provide details regarding manipulation techniques, existing public databases, and key benchmarks for technology evaluation of fake detection methods, including a summary of results from those evaluations. Among all the aspects discussed in the survey, we pay special attention to the latest generation of DeepFakes, highlighting its improvements and challenges for fake detection. In addition to the survey information, we also discuss open issues and future trends that should be considered to advance in the field.