Saved in:
Bibliographic Details
Main Authors: Hu, You, Zhao, Chenzhuo, Mo, Changfa, Liu, Haotian, Li, Xiaobai
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.08211
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908949451636736
author Hu, You
Zhao, Chenzhuo
Mo, Changfa
Liu, Haotian
Li, Xiaobai
author_facet Hu, You
Zhao, Chenzhuo
Mo, Changfa
Liu, Haotian
Li, Xiaobai
contents Modern multimodal generators can now produce scientific figures at near-publishable quality, creating a new challenge for visual forensics and research integrity. Unlike conventional AI-generated natural images, scientific figures are structured, text-dense, and tightly aligned with scholarly semantics, making them a distinct and difficult detection target. However, existing AI-generated image detection benchmarks and methods are almost entirely developed for open-domain imagery, leaving this setting largely unexplored. We present the first benchmark for AI-generated scientific figure detection. To construct it, we develop an agent-based data pipeline that retrieves licensed source papers, performs multimodal understanding of paper text and figures, builds structured prompts, synthesizes candidate figures, and filters them through a review-driven refinement loop. The resulting benchmark covers multiple figure categories, multiple generation sources and aligned real--synthetic pairs. We benchmark representative detectors under zero-shot, cross-generator, and degraded-image settings. Results show that current methods fail dramatically in zero-shot transfer, exhibit strong generator-specific overfitting, and remain fragile under common post-processing corruptions. These findings reveal a substantial gap between existing AIGI detection capabilities and the emerging distribution of high-quality scientific figures. We hope this benchmark can serve as a foundation for future research on robust and generalizable scientific-figure forensics. The dataset is available at https://github.com/Joyce-yoyo/SciFigDetect.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08211
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SciFigDetect: A Benchmark for AI-Generated Scientific Figure Detection
Hu, You
Zhao, Chenzhuo
Mo, Changfa
Liu, Haotian
Li, Xiaobai
Computer Vision and Pattern Recognition
Modern multimodal generators can now produce scientific figures at near-publishable quality, creating a new challenge for visual forensics and research integrity. Unlike conventional AI-generated natural images, scientific figures are structured, text-dense, and tightly aligned with scholarly semantics, making them a distinct and difficult detection target. However, existing AI-generated image detection benchmarks and methods are almost entirely developed for open-domain imagery, leaving this setting largely unexplored. We present the first benchmark for AI-generated scientific figure detection. To construct it, we develop an agent-based data pipeline that retrieves licensed source papers, performs multimodal understanding of paper text and figures, builds structured prompts, synthesizes candidate figures, and filters them through a review-driven refinement loop. The resulting benchmark covers multiple figure categories, multiple generation sources and aligned real--synthetic pairs. We benchmark representative detectors under zero-shot, cross-generator, and degraded-image settings. Results show that current methods fail dramatically in zero-shot transfer, exhibit strong generator-specific overfitting, and remain fragile under common post-processing corruptions. These findings reveal a substantial gap between existing AIGI detection capabilities and the emerging distribution of high-quality scientific figures. We hope this benchmark can serve as a foundation for future research on robust and generalizable scientific-figure forensics. The dataset is available at https://github.com/Joyce-yoyo/SciFigDetect.
title SciFigDetect: A Benchmark for AI-Generated Scientific Figure Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.08211