Experts fail to reliably detect AI-generated histological data

Abstract

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.