Saved in:
Bibliographic Details
Main Authors: Mou, Tingshu, Wei, Zhipeng, Gong, Chao, Chen, Jingjing, Ma, Xingjun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.12967
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913122154971136
author Mou, Tingshu
Wei, Zhipeng
Gong, Chao
Chen, Jingjing
Ma, Xingjun
author_facet Mou, Tingshu
Wei, Zhipeng
Gong, Chao
Chen, Jingjing
Ma, Xingjun
contents The rapid advancement of generative AI has enabled the creation of highly realistic and diverse synthetic images, posing critical challenges for image provenance and misinformation detection. This underscores the urgent need for effective image attribution. However, existing attribution datasets are constrained by limited scale, outdated generation methods, and insufficient semantic diversity - hindering the development of robust and generalizable attribution models. To address these limitations, we introduce ImageAttributionBench, a comprehensive dataset comprising images synthesized by a wide array of advanced generative models with state-of-the-art (SOTA) architectures. Covering multiple real-world semantic domains, the dataset offers rich diversity and scale to support and accelerate progress in image attribution research. To simulate real-world attribution scenarios, we evaluate several SOTA attribution methods on ImageAttributionBench under two challenging settings: (1) training on a standard balanced split and testing on degraded images, and (2) training and testing on semantically disjoint splits. In both cases, current methods exhibit consistently poor performance, revealing significant limitations in their robustness and generalization to unseen semantic content. Our work provides a rigorous benchmark to facilitate the development and evaluation of future image attribution methods.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12967
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ImageAttributionBench: How Far Are We from Generalizable Attribution?
Mou, Tingshu
Wei, Zhipeng
Gong, Chao
Chen, Jingjing
Ma, Xingjun
Computer Vision and Pattern Recognition
The rapid advancement of generative AI has enabled the creation of highly realistic and diverse synthetic images, posing critical challenges for image provenance and misinformation detection. This underscores the urgent need for effective image attribution. However, existing attribution datasets are constrained by limited scale, outdated generation methods, and insufficient semantic diversity - hindering the development of robust and generalizable attribution models. To address these limitations, we introduce ImageAttributionBench, a comprehensive dataset comprising images synthesized by a wide array of advanced generative models with state-of-the-art (SOTA) architectures. Covering multiple real-world semantic domains, the dataset offers rich diversity and scale to support and accelerate progress in image attribution research. To simulate real-world attribution scenarios, we evaluate several SOTA attribution methods on ImageAttributionBench under two challenging settings: (1) training on a standard balanced split and testing on degraded images, and (2) training and testing on semantically disjoint splits. In both cases, current methods exhibit consistently poor performance, revealing significant limitations in their robustness and generalization to unseen semantic content. Our work provides a rigorous benchmark to facilitate the development and evaluation of future image attribution methods.
title ImageAttributionBench: How Far Are We from Generalizable Attribution?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12967