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
- Livestream Shopping Dodges High-Tech Tools to Stop Fake Merch
TikTok and Amazon both said they have advanced technology in place to stop merchants from selling fakes. TikTok said it monitors live video with a mixture of algorithms and humans and Amazon said it ...
- Katy Perry says her own mom was fooled by AI images of her at the Met Gala
Fake images circulating of stars Perry, Rihanna and Selena Gomez at the 2024 Met Gala — which none of them attended — highlight the risks of artificial intelligence.
- Fox News AI Newsletter: Katy Perry says fake Met Gala photos fooled her mom
Katy Perry admits fake Met Gala photos even fooled her mom- Micro business owners are using AI to compete with big brands to level the playing field: report- Randy Travis uses AI for new music after ...
- Katy Perry and Rihanna didn’t attend the Met Gala. But AI-generated images still fooled fans
No, Katy Perry and Rihanna didn’t attend the Met Gala this year. But that didn’t stop AI-generated images from tricking some fans into thinking the stars made appearances on the steps of fashion’s ...
Go deeper with Google Headlines on:
Detecting deep-fake images
[google_news title=”” keyword=”detecting deep-fake images” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Detecting computer-generated images
- OpenAI unveils tool to detect DALL-E images
OpenAI, the Microsoft-backed artificial intelligence company behind the popular image generator DALL-E, on Tuesday announced the launch of a new tool aimed at detecting whether digital images have ...
- RESOURCES: Tools to detect AI and disinformation
Between the increase in disinformation online and the rise of AI, understanding what's real and what isn't can get challenging. However, as tools to fool, fake, and alter media get smarter, so do the ...
- OpenAI Releases ‘Deepfake’ Detector to Disinformation Researchers
The prominent A.I. start-up is also joining an industrywide effort to spot content made with artificial intelligence.
- Sex workers outraged as ‘AI girlfriend’ ads flood Instagram and Facebook: ‘Would be deleted in an instant’
The online chatbots in the ads provide users with AI-generated imagery of realistic, partially clothed and stereotypically pornographic women, including one promising to “get you off in one ...
- AI Detects Deepfake Video Fingerprints
By employing a machine-learning algorithm, the team successfully identified unique digital “fingerprints” left by various AI video generators. This development is crucial as AI-generated content could ...
Go deeper with Google Headlines on:
Detecting computer-generated images
[google_news title=”” keyword=”detecting computer-generated images” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]