Research

Paper

AI LLM February 24, 2026

AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents

Authors

Jiaqi Wu, Yuchen Zhou, Muduo Xu, Zisheng Liang, Simiao Ren, Jiayu Xue, Meige Yang, Siying Chen, Jingheng Huan

Abstract

We present AIForge-Doc, the first dedicated benchmark targeting exclusively diffusion-model-based inpainting in financial and form documents with pixel-level annotation. Existing document forgery datasets rely on traditional digital editing tools (e.g., Adobe Photoshop, GIMP), creating a critical gap: state-of-the-art detectors are blind to the rapidly growing threat of AI-forged document fraud. AIForge-Doc addresses this gap by systematically forging numeric fields in real-world receipt and form images using two AI inpainting APIs -- Gemini 2.5 Flash Image and Ideogram v2 Edit -- yielding 4,061 forged images from four public document datasets (CORD, WildReceipt, SROIE, XFUND) across nine languages, annotated with pixel-precise tampered-region masks in DocTamper-compatible format. We benchmark three representative detectors -- TruFor, DocTamper, and a zero-shot GPT-4o judge -- and find that all existing methods degrade substantially: TruFor achieves AUC=0.751 (zero-shot, out-of-distribution) vs. AUC=0.96 on NIST16; DocTamper achieves AUC=0.563 vs. AUC=0.98 in-distribution, with pixel-level IoU=0.020; GPT-4o achieves only 0.509 -- essentially at chance -- confirming that AI-forged values are indistinguishable to automated detectors and VLMs. These results demonstrate that AIForge-Doc represents a qualitatively new and unsolved challenge for document forensics.

Metadata

arXiv ID: 2602.20569
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-24
Fetched: 2026-02-25 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.20569v1</id>\n    <title>AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents</title>\n    <updated>2026-02-24T05:37:35Z</updated>\n    <link href='https://arxiv.org/abs/2602.20569v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.20569v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We present AIForge-Doc, the first dedicated benchmark targeting exclusively diffusion-model-based inpainting in financial and form documents with pixel-level annotation. Existing document forgery datasets rely on traditional digital editing tools (e.g., Adobe Photoshop, GIMP), creating a critical gap: state-of-the-art detectors are blind to the rapidly growing threat of AI-forged document fraud. AIForge-Doc addresses this gap by systematically forging numeric fields in real-world receipt and form images using two AI inpainting APIs -- Gemini 2.5 Flash Image and Ideogram v2 Edit -- yielding 4,061 forged images from four public document datasets (CORD, WildReceipt, SROIE, XFUND) across nine languages, annotated with pixel-precise tampered-region masks in DocTamper-compatible format. We benchmark three representative detectors -- TruFor, DocTamper, and a zero-shot GPT-4o judge -- and find that all existing methods degrade substantially: TruFor achieves AUC=0.751 (zero-shot, out-of-distribution) vs. AUC=0.96 on NIST16; DocTamper achieves AUC=0.563 vs. AUC=0.98 in-distribution, with pixel-level IoU=0.020; GPT-4o achieves only 0.509 -- essentially at chance -- confirming that AI-forged values are indistinguishable to automated detectors and VLMs. These results demonstrate that AIForge-Doc represents a qualitatively new and unsolved challenge for document forensics.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-24T05:37:35Z</published>\n    <arxiv:comment>17 pages, 10 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Jiaqi Wu</name>\n    </author>\n    <author>\n      <name>Yuchen Zhou</name>\n    </author>\n    <author>\n      <name>Muduo Xu</name>\n    </author>\n    <author>\n      <name>Zisheng Liang</name>\n    </author>\n    <author>\n      <name>Simiao Ren</name>\n    </author>\n    <author>\n      <name>Jiayu Xue</name>\n    </author>\n    <author>\n      <name>Meige Yang</name>\n    </author>\n    <author>\n      <name>Siying Chen</name>\n    </author>\n    <author>\n      <name>Jingheng Huan</name>\n    </author>\n  </entry>"
}