Amplifying The Uncanny
This work addresses aesthetic exploration in AI-generated art for artists and researchers, but it is incremental as it builds on existing deepfake techniques.
The paper tackles the problem of generating deepfake images by inverting the typical optimization process, instead creating images that the system predicts as fake to maximize data unlikelihood and amplify uncanny aesthetics, resulting in a series of artworks called 'Being Foiled'.
Deep neural networks have become remarkably good at producing realistic deepfakes, images of people that (to the untrained eye) are indistinguishable from real images. Deepfakes are produced by algorithms that learn to distinguish between real and fake images and are optimised to generate samples that the system deems realistic. This paper, and the resulting series of artworks Being Foiled explore the aesthetic outcome of inverting this process, instead optimising the system to generate images that it predicts as being fake. This maximises the unlikelihood of the data and in turn, amplifies the uncanny nature of these machine hallucinations.