Frequency analysis reveals typical artefacts in computer-generated images. via RUB, Marquard
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 analyse the objects in the frequency domain, an established signal processing technique.
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 recognises it as a fake.
In recent years, this technique has helped make deep-fake images more and more authentic. On the website www.whichfaceisreal.com, 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 artefacts
To date, deep-fake images have been analysed 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.
The 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 recognise computer-generated images.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Detecting deep-fake images
- Demi Lovato Talks Healing, Being Misunderstood Days After Max Ehrich Spliton September 28, 2020 at 8:22 pm
Demi Lovato shared a message about healing and being misunderstood just days after her split from Max Ehrich. The latter claimed he only learned about their split from a tabloid.
- Demi Lovato and Max Ehrich end their engagement after 2 monthson September 24, 2020 at 4:08 pm
"It was a tough decision, but Demi and Max have decided to go their separate ways to focus on their respective careers," says the source. "They have respect and love for one another and will always ...
- Why Demi Lovato's Fans Think Her Relationship With Max Ehrich Is in Troubleon September 24, 2020 at 2:24 pm
Demi Lovato has stopped liking fiancé Max Ehrich's Instagram posts—one of a few reasons why fans are raising their eyebrows about her romance.
Go deeper with Google Headlines on:
Detecting deep-fake images
Go deeper with Bing News on:
Detecting computer-generated images
- Expert says detecting deepfakes almost impossibleon September 30, 2020 at 9:38 am
The technology to produce fake video and audio has become sophisticated enough to make doctored or wholly fabricated images and sound impossible for the public to detect, Hany Farid, professor at the ...
- Simple User Interface for Gel Documentationon September 30, 2020 at 12:04 am
575-640 nm and 513-557 nm emission filters were placed in the filter slot located on top of the system to detect GelRed and GelGreen wavelengths. Table 1 shows the image capture data for each ...
- Consider the Promises and Challenges of Medical Image Analyses Using Machine Learningon September 29, 2020 at 5:00 pm
and conditions that may be hard to detect without the supplemental technology. Images are the largest source of data in healthcare and, at the same time, one of the most challenging sources to analyze ...
- Piezoelectric and laser ultrasonic system takes 3-D ultrasound images of solidson September 25, 2020 at 5:18 am
A new system, developed by Tohoku University researchers in Japan in collaboration with Los Alamos National Laboratory in the US, takes 3-D images that can detect defects in metallic structures.
- PLUS takes 3D ultrasound images of solidson September 24, 2020 at 5:00 pm
A new system, developed by Tohoku University researchers in Japan in collaboration with Los Alamos National Laboratory in the US, takes 3D images that can detect ... the waves generated in a ...