DeepAI AI Chat
Log In Sign Up

Detecting GAN-generated Imagery using Color Cues

by   Scott McCloskey, et al.
Honeywell International Inc.

Image forensics is an increasingly relevant problem, as it can potentially address online disinformation campaigns and mitigate problematic aspects of social media. Of particular interest, given its recent successes, is the detection of imagery produced by Generative Adversarial Networks (GANs), e.g. `deepfakes'. Leveraging large training sets and extensive computing resources, recent work has shown that GANs can be trained to generate synthetic imagery which is (in some ways) indistinguishable from real imagery. We analyze the structure of the generating network of a popular GAN implementation, and show that the network's treatment of color is markedly different from a real camera in two ways. We further show that these two cues can be used to distinguish GAN-generated imagery from camera imagery, demonstrating effective discrimination between GAN imagery and real camera images used to train the GAN.


page 1

page 4


Source Generator Attribution via Inversion

With advances in Generative Adversarial Networks (GANs) leading to drama...

Deep Snow: Synthesizing Remote Sensing Imagery with Generative Adversarial Nets

In this work we demonstrate that generative adversarial networks (GANs) ...

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

The advent of Generative Adversarial Network (GAN) architectures has giv...

Evaluating a GAN for enhancing camera simulation for robotics

Given the versatility of generative adversarial networks (GANs), we seek...

Modeling Camera Effects to Improve Deep Vision for Real and Synthetic Data

Recent work has focused on generating synthetic imagery and augmenting r...

Multiband SAS Imagery

Advances in unmanned synthetic aperture sonar (SAS) imaging platforms al...

End-to-End Deep Structured Models for Drawing Crosswalks

In this paper we address the problem of detecting crosswalks from LiDAR ...