A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection

TL;DR

This paper challenges the belief that CNN-generated images inherently exhibit high frequency Fourier spectrum discrepancies, demonstrating that such spectral features can be mitigated through minor architecture changes, thus questioning their reliability for detection.

Contribution

The study constructs counterexamples showing spectral discrepancies can be avoided, and demonstrates that high frequency Fourier spectrum decay is not a robust indicator for CNN-generated image detection.

Findings

Spectral discrepancies are not inherent to CNN-generated images.

Minor architecture changes can produce spectra that bypass detection.

Fourier spectrum decay features are unreliable for robust detection.

Abstract

CNN-based generative modelling has evolved to produce synthetic images indistinguishable from real images in the RGB pixel space. Recent works have observed that CNN-generated images share a systematic shortcoming in replicating high frequency Fourier spectrum decay attributes. Furthermore, these works have successfully exploited this systematic shortcoming to detect CNN-generated images reporting up to 99% accuracy across multiple state-of-the-art GAN models. In this work, we investigate the validity of assertions claiming that CNN-generated images are unable to achieve high frequency spectral decay consistency. We meticulously construct a counterexample space of high frequency spectral decay consistent CNN-generated images emerging from our handcrafted experiments using DCGAN, LSGAN, WGAN-GP and StarGAN, where we empirically show that this frequency discrepancy can be avoided by a minor architecture change in the last upsampling operation. We subsequently use images from this counterexample space to successfully bypass the recently proposed forensics detector which leverages on high frequency Fourier spectrum decay attributes for CNN-generated image detection. Through this study, we show that high frequency Fourier spectrum decay discrepancies are not inherent characteristics for existing CNN-based generative models--contrary to the belief of some existing work--, and such features are not robust to perform synthetic image detection. Our results prompt re-thinking of using high frequency Fourier spectrum decay attributes for CNN-generated image detection. Code and models are available at https://keshik6.github.io/Fourier-Discrepancies-CNN-Detection/