The Unwinnable Arms Race of AI Image Detection
This addresses the challenge of distinguishing synthetic from real images in AI, with incremental insights into dataset complexity effects.
The paper investigates the conditions under which discriminators are disadvantaged in detecting AI-generated images, finding that both very simple and highly complex datasets reduce detectability, while intermediate-complexity datasets are most favorable for detection.
The rapid progress of image generative AI has blurred the boundary between synthetic and real images, fueling an arms race between generators and discriminators. This paper investigates the conditions under which discriminators are most disadvantaged in this competition. We analyze two key factors: data dimensionality and data complexity. While increased dimensionality often strengthens the discriminators ability to detect subtle inconsistencies, complexity introduces a more nuanced effect. Using Kolmogorov complexity as a measure of intrinsic dataset structure, we show that both very simple and highly complex datasets reduce the detectability of synthetic images; generators can learn simple datasets almost perfectly, whereas extreme diversity masks imperfections. In contrast, intermediate-complexity datasets create the most favorable conditions for detection, as generators fail to fully capture the distribution and their errors remain visible.