Open Access

REVIEW

A Survey of GAN-Generated Fake Faces Detection Method Based on Deep Learning

Xin Liu^*, Xiao Chen

Nanjing University of Information Science and Technology, Nanjing, 210044, China

* Corresponding Author: Xin Liu. Email:

Journal of Information Hiding and Privacy Protection 2020, 2(2), 87-94. https://doi.org/10.32604/jihpp.2020.09839

Received 21 May 2020; Accepted 28 June 2020; Issue published 11 November 2020

Abstract

In recent years, with the rapid growth of generative adversarial networks (GANs), a photo-realistic face can be easily generated from a random vector. Moreover, the faces generated by advanced GANs are very realistic. It is reasonable to acknowledge that even a well-trained viewer has difficulties to distinguish artificial from real faces. Therefore, detecting the face generated by GANs is a necessary work. This paper mainly introduces some methods to detect GAN-generated fake faces, and analyzes the advantages and disadvantages of these models based on the network structure and evaluation indexes, and the results obtained in the respective data sets. On this basis, the challenges faced in this field and future research directions are discussed.

---

Keywords

---

Citations