Which Face is Real? Using Frequency Analysis to Identify “Deep-Fake” Images

This method exposes fake images created by computer algorithms rather than by humans.

They look deceptively real, but they are made by computers: so-called deep-fake images are generated by machine learning algorithms, and humans are pretty much unable to distinguish them from real photos. Researchers at the Horst Görtz Institute for IT Security at Ruhr-Universität Bochum and the Cluster of Excellence “Cyber Security in the Age of Large-Scale Adversaries” (Casa) have developed a new method for efficiently identifying deep-fake images. To this end, they analyze the objects in the frequency domain, an established signal processing technique.

Frequency Analysis Fake Images

Frequency analysis revelas typical artefacts in computer-generated images. Credit: © RUB, Marquard

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*, so that other groups can reproduce their results.

Interaction of two algorithms results in new images

Deep-fake images — a portmanteau word from “deep learning” for machine learning and “fake” — are generated with the help of computer models, so-called Generative Adversarial Networks, GANs for short. Two algorithms work together in these networks: the first algorithm creates random images based on certain input data. The second algorithm needs to decide whether the image is a fake or not. If the image is found to be a fake, the second algorithm gives the first algorithm the command to revise the image — until it no longer recognizes it as a fake.

Members of the Bochum-based research team include: Thorsten Holz, Lea Schönherr, Joel Frank and Thorsten Eisenhofer (left to right). Credit: RUB, Marquard

In recent years, this technique has helped make deep-fake images more and more authentic. On the website**, users can check if they’re able to distinguish fakes from original photos. “In the era of fake news, it can be a problem if users don’t have the ability to distinguish computer-generated images from originals,” says Professor Thorsten Holz from the Chair for Systems Security.

For their analysis, the Bochum-based researchers used the data sets that also form the basis of the above-mentioned page “Which face is real”. In this interdisciplinary project, Joel Frank, Thorsten Eisenhofer and Professor Thorsten Holz from the Chair for Systems Security cooperated with Professor Asja Fischer from the Chair of Machine Learning as well as Lea Schönherr and Professor Dorothea Kolossa from the Chair of Digital Signal Processing.

Frequency analysis reveals typical artifacts

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.

Images of people transformed into the frequency domain: the upper left corner represents low-frequency image areas, the lower right corner represents high-frequency areas. On the left, you can see the transformation of a photo of a real person: the frequency range is evenly distributed. The transformation of the computer-generated photo (right) contains a characteristic grid structure in the high-frequency range – a typical artifact. Credit: © RUB, Lehrstuhl für Systemsicherheit

The analysis has shown that images generated by GANs exhibit artifacts in the high-frequency range. For example, a typical grid structure emerges in the frequency representation of fake images. “Our experiments showed that these artifacts 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 artifacts 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.”


Reference: “Leveraging Frequency Analysis for Deep Fake Image Recognition” by Joel Frank, Thorsten Eisenhofer, Lea Schonherr, Asja Fischer, Dorothea Kolossa and Thorsten Holz, 2020, International Conference on Machine Learning (ICML).


* Code available at GitHub.

** Website:


View Comments

  • Unfortunately, it will be just as easy to use this technique to remove the artifacts from "deep fake" photographs in the next generation of development.

    • Yep, The moment that DeepFakes was created I knew what was coming ... it aint here yet, but it almost is, and we aren't in the least bit ready for it.

Recent Posts

How Do You Treat Untreatable Infections? Princeton Researchers Have Created a New Bacteria-Killing Compound

A mechanism used by bacteria to defend themselves could lead to the development of new…

February 6, 2023

Groundbreaking Discovery of Hidden Molten Rock Layer Under Earth’s Tectonic Plates

Scientists have discovered a new layer of partly molten rock under the Earth’s crust that…

February 6, 2023

Bad News: Warming Oceans Have Decimated Marine Parasites

Over 100 years of preserved fish specimens provide a unique look at parasite population trends…

February 6, 2023

Study Provides Darkest-Ever View of Primordial Interstellar Ices

Researchers used the James Webb Space Telescope to examine primordial interstellar ices. An international team…

February 6, 2023

Outstanding Results: New Method Allows Struggling Children To Crack the Reading Code

Children learn to read faster when they are given appropriate challenges. Reading is the foundation…

February 6, 2023

“A Missing Piece of the Puzzle” – Researchers Investigate New Cause of Severe Obesity

Leipzig researchers examine a new cause of severe obesity. Obesity and obesity-related illnesses are major…

February 6, 2023