Is Artificial Intelligence Generated Image Detection a Solved Problem?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Ziqiang, Yan, Jiazhen, He, Ziwen, Zeng, Kai, Jiang, Weiwei, Xiong, Lizhi, Fu, Zhangjie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915562541547520
author Li, Ziqiang
Yan, Jiazhen
He, Ziwen
Zeng, Kai
Jiang, Weiwei
Xiong, Lizhi
Fu, Zhangjie
author_facet Li, Ziqiang
Yan, Jiazhen
He, Ziwen
Zeng, Kai
Jiang, Weiwei
Xiong, Lizhi
Fu, Zhangjie
contents The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinformation, deepfakes, and copyright infringement. Although numerous Artificial Intelligence Generated Image (AIGI) detectors have been proposed, often reporting high accuracy, their effectiveness in real-world scenarios remains questionable. To bridge this gap, we introduce AIGIBench, a comprehensive benchmark designed to rigorously evaluate the robustness and generalization capabilities of state-of-the-art AIGI detectors. AIGIBench simulates real-world challenges through four core tasks: multi-source generalization, robustness to image degradation, sensitivity to data augmentation, and impact of test-time pre-processing. It includes 23 diverse fake image subsets that span both advanced and widely adopted image generation techniques, along with real-world samples collected from social media and AI art platforms. Extensive experiments on 11 advanced detectors demonstrate that, despite their high reported accuracy in controlled settings, these detectors suffer significant performance drops on real-world data, limited benefits from common augmentations, and nuanced effects of pre-processing, highlighting the need for more robust detection strategies. By providing a unified and realistic evaluation framework, AIGIBench offers valuable insights to guide future research toward dependable and generalizable AIGI detection.Data and code are publicly available at: https://github.com/HorizonTEL/AIGIBench.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12335
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Is Artificial Intelligence Generated Image Detection a Solved Problem?
Li, Ziqiang
Yan, Jiazhen
He, Ziwen
Zeng, Kai
Jiang, Weiwei
Xiong, Lizhi
Fu, Zhangjie
Computer Vision and Pattern Recognition
Cryptography and Security
The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinformation, deepfakes, and copyright infringement. Although numerous Artificial Intelligence Generated Image (AIGI) detectors have been proposed, often reporting high accuracy, their effectiveness in real-world scenarios remains questionable. To bridge this gap, we introduce AIGIBench, a comprehensive benchmark designed to rigorously evaluate the robustness and generalization capabilities of state-of-the-art AIGI detectors. AIGIBench simulates real-world challenges through four core tasks: multi-source generalization, robustness to image degradation, sensitivity to data augmentation, and impact of test-time pre-processing. It includes 23 diverse fake image subsets that span both advanced and widely adopted image generation techniques, along with real-world samples collected from social media and AI art platforms. Extensive experiments on 11 advanced detectors demonstrate that, despite their high reported accuracy in controlled settings, these detectors suffer significant performance drops on real-world data, limited benefits from common augmentations, and nuanced effects of pre-processing, highlighting the need for more robust detection strategies. By providing a unified and realistic evaluation framework, AIGIBench offers valuable insights to guide future research toward dependable and generalizable AIGI detection.Data and code are publicly available at: https://github.com/HorizonTEL/AIGIBench.
title Is Artificial Intelligence Generated Image Detection a Solved Problem?
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2505.12335