Abstract
AI-generated image detectors are often evaluated on benchmarks where real and synthetic images differ in content, quality, or generation artifacts, allowing models to rely on dataset-specific cues and fail on unfamiliar generators or processed images. Existing datasets provide limited support for evaluating these challenges jointly across diverse visual content. We introduce REALIS, a dataset of 1.43 million real and synthetic images generated by 42 modern text-to-image models, including the latest proprietary systems such as Nano Banana 2. REALIS combines prompts derived from real images, quality filtering, and stratified sampling to reduce class-specific shortcuts while preserving content diversity. We further introduce REALIS-Expert, a stress-test subset for high-quality synthetic images, where real and generated samples are selected with closely matched semantic and visual characteristics. We also propose a robustness protocol covering 35 transformations at five severity levels to analyze detector behavior under image processing. Based on REALIS, our benchmark evaluates pretrained detectors, fine-tuned models, and zero-shot vision-language models under generator and post-processing shifts. On the hardest processed split, the best pretrained conventional detector achieves 0.550 ROC-AUC, compared with 0.752 for the best REALIS-trained detector. REALIS provides a unified framework for measuring and improving the reliability of AI-image detectors under conditions that better reflect real-world use.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Gushchin, A., Abud, K., Bychkov, G., Shumitskaya, E., Filippov, A., Lavrushkin, S., Vatolin, D. S., & Antsiferova, A. (2026). REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection. https://omanscience.com/en/articles/realis-a-curated-dataset-for-studying-the-challenges-of-ai-image-detection
MLA 9
Gushchin, Aleksandr, et al. "REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection." https://omanscience.com/en/articles/realis-a-curated-dataset-for-studying-the-challenges-of-ai-image-detection.
Chicago (author–date)
Gushchin, Aleksandr, Khaled Abud, Georgii Bychkov, Ekaterina Shumitskaya, Artem Filippov, Sergey Lavrushkin, Dmitriy S. Vatolin, and Anastasia Antsiferova. 2026. "REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection." https://omanscience.com/en/articles/realis-a-curated-dataset-for-studying-the-challenges-of-ai-image-detection.
Harvard
Gushchin, A., Abud, K., Bychkov, G., Shumitskaya, E., Filippov, A., Lavrushkin, S., Vatolin, D. S. and Antsiferova, A. (2026) 'REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection', Available at: https://omanscience.com/en/articles/realis-a-curated-dataset-for-studying-the-challenges-of-ai-image-detection.
Vancouver
Gushchin A, Abud K, Bychkov G, Shumitskaya E, Filippov A, Lavrushkin S, et al. REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection. https://omanscience.com/en/articles/realis-a-curated-dataset-for-studying-the-challenges-of-ai-image-detection
IEEE
A. Gushchin, K. Abud, G. Bychkov, E. Shumitskaya, A. Filippov, S. Lavrushkin, D. S. Vatolin, and A. Antsiferova, "REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection," https://omanscience.com/en/articles/realis-a-curated-dataset-for-studying-the-challenges-of-ai-image-detection.