Learning to Detect Fake Face Images in the Wild

09/24/2018
by   Chih-Chung Hsu, et al.
0

Although Generative Adversarial Network (GAN) can be used to generate the realistic image, improper use of these technologies brings hidden concerns. For example, GAN can be used to generate a tampered video for specific people and inappropriate events, creating images that are detrimental to a particular person, and may even affect that personal safety. In this paper, we will develop a deep forgery discriminator (DeepFD) to efficiently and effectively detect the computer-generated images. Directly learning a binary classifier is relatively tricky since it is hard to find the common discriminative features for judging the fake images generated from different GANs. To address this shortcoming, we adopt contrastive loss in seeking the typical features of the synthesized images generated by different GANs and follow by concatenating a classifier to detect such computer-generated images. Experimental results demonstrate that the proposed DeepFD successfully detected 94.7 generated by several state-of-the-art GANs

READ FULL TEXT

Authors

page 2

page 4

02/27/2019

On the generalization of GAN image forensics

Recently the GAN generated face images are more and more realistic with ...
07/04/2021

Auxiliary-Classifier GAN for Malware Analysis

Generative adversarial networks (GAN) are a class of powerful machine le...
07/16/2017

Generative Adversarial Network based on Resnet for Conditional Image Restoration

The GANs promote an adversarive game to approximate complex and jointed ...
05/23/2021

CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes

Malicious application of deepfakes (i.e., technologies can generate targ...
06/24/2020

PhishGAN: Data Augmentation and Identification of Homoglpyh Attacks

Homoglyph attacks are a common technique used by hackers to conduct phis...
04/16/2020

On the use of Benford's law to detect GAN-generated images

The advent of Generative Adversarial Network (GAN) architectures has giv...
05/26/2021

Pattern Detection in the Activation Space for Identifying Synthesized Content

Generative Adversarial Networks (GANs) have recently achieved unpreceden...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.