Researchers from Ruhr-University Bochum have presented a new method of identifying computer-generated images, typically by Generative Adversarial Networks, or the so-called deep-fakes. To date, deep-fake images have been analyzed using complex statistical methods. The Bochum group chose a different approach by converting the images into the frequency domain using the discrete cosine transform. The generated image is thus expressed as the sum of many different cosine functions.

Natural images consist mainly of low-frequency functions. Their analysis has shown that images generated by GANs exhibit artefacts in the high-frequency range. For example, a typical grid structure emerges in the frequency representation of fake images. "Our experiments showed that these artefacts do not only occur in GAN generated images. They are a structural problem of all deep learning algorithms," explains Joel Frank from the Chair for Systems Security. "We assume that the artefacts described in our study will always tell us whether the image is a deep-fake image created by machine learning," adds Frank. "Frequency analysis is therefore an effective way to automatically recognize computer-generated images."

The team presented their work at the International Conference on Machine Learning (ICML) on 15 July 2020, one of the leading conferences in the field of machine learning. Additionally, the researchers make their code freely available online at https://github.com/RUB-SysSec/GANDCTAnalysis, so that other groups can reproduce their results.