DeepAI AI Chat
Log In Sign Up

Detecting GAN-generated Images by Orthogonal Training of Multiple CNNs

by   Sara Mandelli, et al.

In the last few years, we have witnessed the rise of a series of deep learning methods to generate synthetic images that look extremely realistic. These techniques prove useful in the movie industry and for artistic purposes. However, they also prove dangerous if used to spread fake news or to generate fake online accounts. For this reason, detecting if an image is an actual photograph or has been synthetically generated is becoming an urgent necessity. This paper proposes a detector of synthetic images based on an ensemble of Convolutional Neural Networks (CNNs). We consider the problem of detecting images generated with techniques not available at training time. This is a common scenario, given that new image generators are published more and more frequently. To solve this issue, we leverage two main ideas: (i) CNNs should provide orthogonal results to better contribute to the ensemble; (ii) original images are better defined than synthetic ones, thus they should be better trusted at testing time. Experiments show that pursuing these two ideas improves the detector accuracy on NVIDIA's newly generated StyleGAN3 images, never used in training.


page 1

page 2

page 3

page 4


Syn-Att: Synthetic Speech Attribution via Semi-Supervised Unknown Multi-Class Ensemble of CNNs

With the huge technological advances introduced by deep learning in audi...

Deep Image Fingerprint: Accurate And Low Budget Synthetic Image Detector

The generation of high-quality images has become widely accessible and i...

TI-CNN: Convolutional Neural Networks for Fake News Detection

With the development of social networks, fake news for various commercia...

A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain

We propose a novel universal detector for detecting images generated by ...

Detecting and Localizing Copy-Move and Image-Splicing Forgery

In the world of fake news and deepfakes, there have been an alarmingly l...

Detecting GAN generated errors

Despite an impressive performance from the latest GAN for generating hyp...

Incremental learning for the detection and classification of GAN-generated images

Current developments in computer vision and deep learning allow to autom...