RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection
This work addresses the need for interpretable and robust fake image detection methods for security and verification applications, though it is incremental as it builds on existing detectors.
The paper tackles the challenge of detecting AI-generated images by introducing a statistically grounded framework that produces interpretable probability scores based on real-image populations, achieving robust detection across diverse settings without requiring training.
As generative models continue to evolve, detecting AI-generated images remains a critical challenge. While effective detection methods exist, they often lack formal interpretability and may rely on implicit assumptions about fake content, potentially limiting robustness to distributional shifts. In this work, we introduce a rigorous, statistically grounded framework for fake image detection that focuses on producing a probability score interpretable with respect to the real-image population. Our method leverages the strengths of multiple existing detectors by combining training-free statistics. We compute p-values over a range of test statistics and aggregate them using classical statistical ensembling to assess alignment with the unified real-image distribution. This framework is generic, flexible, and training-free, making it well-suited for robust fake image detection across diverse and evolving settings.