They look convincingly real, and it is very challenging to distinguish them from real photos. However, researchers have found a new way to identify them.
These images (called deep-fake images) are created by machine learning algorithms and it is very challenging to distinguish them from real photos. Researchers have found a new method to effectively identify those images. They analyze the objects in the frequency domain and set up a signal processing technique.
Interaction of two algorithms results in new images
Deep-fake images - 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.
Frequency analysis reveals typical artefacts in computer-generated images. Credit: © RUB, Marquard
Frequency analysis reveals typical artefacts
Nowadays, deep-fake images have been analysed using complex statistical methods. The research group chose a different approach by converting the images into the frequency domain using the discrete cosine transform. The generated image is then 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."
Source: Science Daily
About us: TMA Solutions was established in 1997 to provide quality software outsourcing services to leading companies worldwide. We are one of the largest software outsourcing companies in Vietnam with 2,500 engineers.
Visit us at https://www.tmasolutions.com/.
No comments:
Post a Comment