WHICH HUMAN FACES CAN AN AI GENERATE? LACK OF DIVERSITY IN THIS PERSON DOES NOT EXIST
Keywords:Computer Vision, StyleGAN, This Person Does Not Exist, Dataset Auditing, Deepfake
AbstractIn this abstract we show the results of an interdisciplinary research in which we audit fake human faces generated by the website This Person Does Not Exist (TPDNE), and discuss how this system can help perpetuate normativities supported by a dependency on a limited database. Our analysis is centered on the “default generic face” that we created by overlapping random samples of fake human faces generated by TPDNE's algorithms – a version of Generative Adversarial Network, the StyleGAN2. To carry these experiments, we built a database with 4100 fake human faces taken from TPDNE via web scraping; we analysed them through a Python language script; and discussed behaviours identified in results. Our analyses are based on the use of images, called “cluster-images”, created from this overlapping of N arbitrary fake human faces by the TPDNE's algorithm. Our experiments showed that, independently of the group of fake human faces sampled, the same generic white face always appeared as a result. These results intrigue particularly because the lack of diversity of TPDNE's generated faces is not a mere problem to be fixed in this system in this digital infrastructure, but a dynamic of reinforcing standards that historically regulate bodies, territories and practices.
How to Cite
Sequeira, L. N., Moreschi, B., & Santos, V. A. A. dos. (2021). WHICH HUMAN FACES CAN AN AI GENERATE? LACK OF DIVERSITY IN THIS PERSON DOES NOT EXIST. AoIR Selected Papers of Internet Research, 2021. https://doi.org/10.5210/spir.v2021i0.12240