AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908849909268480 |
|---|---|
| author | Wu, Jiaqi Zhou, Yuchen Xu, Muduo Liang, Zisheng Ren, Simiao Xue, Jiayu Yang, Meige Chen, Siying Huan, Jingheng |
| author_facet | Wu, Jiaqi Zhou, Yuchen Xu, Muduo Liang, Zisheng Ren, Simiao Xue, Jiayu Yang, Meige Chen, Siying Huan, Jingheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20569 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents Wu, Jiaqi Zhou, Yuchen Xu, Muduo Liang, Zisheng Ren, Simiao Xue, Jiayu Yang, Meige Chen, Siying Huan, Jingheng Computer Vision and Pattern Recognition 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. |
| title | AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.20569 |