RT Journal Article
SR Electronic
T1 Experts fail to reliably detect AI-generated histological data
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2024.01.23.576647
DO 10.1101/2024.01.23.576647
A1 Hartung, Jan
A1 Reuter, Stefanie
A1 Kulow, Vera Anna
A1 Fähling, Michael
A1 Spreckelsen, Cord
A1 Mrowka, Ralf
YR 2024
UL http://biorxiv.org/content/early/2024/01/25/2024.01.23.576647.abstract
AB AI-based methods to generate images have seen unprecedented advances in recent years challenging both image forensic and human perceptual capabilities. Accordingly, they are expected to play an increasingly important role in the fraudulent fabrication of data. This includes images with complicated intrinsic structures like histological tissue samples, which are harder to forge manually. We use stable diffusion, one of the most recent generative algorithms, to create such a set of artificial histological samples and in a large study with over 800 participants, we study the ability of human subjects to discriminate between such artificial and genuine histological images. Although they perform better than naive participants, we find that even experts fail to reliably identify fabricated data. While participant performance depends on the amount of training data used, even low quantities result in convincing images, necessitating methods to detect fabricated data and technical standards such as C2PA to secure data integrity.Competing Interest StatementThe authors have declared no competing interest.