Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Zexi Jia, Zhiqiang Yuan, Xiaoyue Duan, Jinchao Zhang, Jie Zhou, Anil K. Jain• 2026

Related benchmarks

TaskDatasetResultRank
AI-generated image detectionGenImage
Midjourney Detection Rate96
154
Synthetic Image DetectionGANs dataset
Mean ACC98.9
40
Fake Image DetectionDiffusion
Accuracy95.3
20
AI-generated image detectionOjha Diffusion Benchmark 1.0 (test)
DALL-E Acc98.1
20
AI-generated image detectionForenSynths v1 (test)
ProGAN Accuracy99.9
20
AI-generated image detectionFakeForm Photojournalism
Accuracy0.873
10
AI-generated image detectionFakeForm Poster
Accuracy94.5
10
AI-generated image detectionFakeForm Watercolor
Accuracy75.5
10
AI-generated image detectionFakeForm Ukiyo-e
Accuracy87.5
10
AI-generated image detectionFakeForm Paper Cutting
Accuracy92.5
10
Showing 10 of 42 rows

Other info

Follow for update