RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection

January 26, 2026 ยท Grace Period ยท ๐Ÿ› AISTATS 2026

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Haim Zisman, Uri Shaham arXiv ID 2601.18900 Category cs.CV: Computer Vision Cross-listed cs.LG, stat.ML Citations 0 Venue AISTATS 2026
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision