Deepfakes: we need to re-think the concept of “real” images

Janis Keuper, Margret Keuper

Keywords: Deep Fake, Generated Image Detection

TL;DR: We argue that current approaches towards the detection of generated images neglect a clear and sound definition of "real" (images).

Abstract:

The wide availability and low usability barrier of modern image generation mod-
els has triggered the reasonable fear of criminal misconduct and negative social
implications. The machine learning community has been engaging this problem
with an extensive series of publications proposing algorithmic solutions for the
detection of “fake”, e.g. entirely generated or partially manipulated images. While
there is undoubtedly some progress towards technical solutions of the problem,
we argue that current and prior work is focusing too much on generative algo-
rithms and “fake” data-samples, neglecting a clear definition and data collection
of “real” images.

The fundamental question *“what is a real image?”* might appear to be quite
philosophical, but our analysis shows that the development and evaluation of
basically all current “fake”-detection methods is relying on only a few, quite old
low-resolution datasets of “real” images like ImageNet. However, the technology
for the acquisition of “real” images, aka taking photos, has drastically evolved
over the last decade: Today, over 90% of all photographs are produced by smart-
phones which typically use algorithms to compute an image from multiple inputs
(over time) from multiple sensors. Based on the fact that these image formation
algorithms are typically neural network architectures which are closely related to
“fake”-image generators, we state the position that today, **we need to re-think
the concept of “real” images**.

The purpose of this position paper is to raise the awareness of the current short-
comings in this active field of research and to trigger an open discussion wether
the detection of “fake” images is a sound objective at all. At the very least, we
need a clear technical definition of “real” images and new benchmark datasets.

Submission Number: 30