DeepAI AI Chat
Log In Sign Up

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

by   Nicolò Bonettini, et al.
Università di Padova
Politecnico di Milano

The advent of Generative Adversarial Network (GAN) architectures has given anyone the ability of generating incredibly realistic synthetic imagery. The malicious diffusion of GAN-generated images may lead to serious social and political consequences (e.g., fake news spreading, opinion formation, etc.). It is therefore important to regulate the widespread distribution of synthetic imagery by developing solutions able to detect them. In this paper, we study the possibility of using Benford's law to discriminate GAN-generated images from natural photographs. Benford's law describes the distribution of the most significant digit for quantized Discrete Cosine Transform (DCT) coefficients. Extending and generalizing this property, we show that it is possible to extract a compact feature vector from an image. This feature vector can be fed to an extremely simple classifier for GAN-generated image detection purpose.


Fighting deepfakes by detecting GAN DCT anomalies

Synthetic multimedia content created through AI technologies, such as Ge...

Detecting GAN-generated Imagery using Color Cues

Image forensics is an increasingly relevant problem, as it can potential...

Intriguing properties of synthetic images: from generative adversarial networks to diffusion models

Detecting fake images is becoming a major goal of computer vision. This ...

Learning to Detect Fake Face Images in the Wild

Although Generative Adversarial Network (GAN) can be used to generate th...

Detecting GAN generated errors

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

Policy Gradient Stock GAN for Realistic Discrete Order Data Generation in Financial Markets

This study proposes a new generative adversarial network (GAN) for gener...