CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection

2026-05-22

AI Summary

Existing methods for detecting AI-generated images struggle to balance generalization capability and computational efficiency, particularly lacking robustness across generative models and domains. This work presents the first systematic investigation of cross-domain detection and introduces CoDA, a lightweight detector that leverages theoretical insights into the non-uniformity differences in color distributions between real and synthetic images. Built upon a noise quantification probe with only 1.48 million parameters, CoDA achieves state-of-the-art performance on both standard benchmarks and FakeForm—a newly proposed cross-domain evaluation suite. The method significantly improves cross-domain detection accuracy while maintaining high computational efficiency.

Abstract

AI-generated image detection faces a persistent trade-off between generalization and efficiency: lightweight artifact-based methods often degrade on unseen generators or domains, whereas more robust large-scale models are computationally expensive. Meanwhile, existing benchmarks mainly focus on cross-model evaluation in photorealistic settings, leaving cross-domain robustness underexplored. To address this gap, we introduce FakeForm, a large-scale benchmark with approximately 370,000 images across 62 diverse domains for both cross-model and cross-domain evaluation. Motivated by this broader setting, we revisit color-distribution probing as an efficient complementary cue for AI-generated image detection. We observe that, especially for photographic content, real photographs tend to exhibit smoother and more stable color patterns, whereas synthetic images often show characteristic color imbalances introduced by neural generation. Based on this observation, we propose CoDA, a compact 1.48M-parameter detector built on a Noise-Quantization Probe, together with a theoretical analysis linking probe responses to color non-uniformity. Experiments show that CoDA achieves state-of-the-art performance on standard benchmarks and the best results on the challenging cross-domain evaluation of FakeForm, while remaining highly competitive in cross-model photorealistic settings. These results suggest that persistent generative artifacts can provide a practical foundation for efficient and robust AI-generated image detection. The models and FakeForm benchmark will be made publicly available.

Problem

• AI-generated image detection
• generalization
• efficiency
• cross-domain robustness
• color distribution

Innovation

• color distribution probing
• AI-generated image detection
• cross-domain robustness
• lightweight detector
• FakeForm benchmark