Pith.

Computer Vision and Pattern Recognition · arXiv:2602.20569 v2 · submitted 24 Feb 2026

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

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

show 1 more author

Jingheng Huan

The paper says

“These results demonstrate that AIForge-Doc represents a qualitatively new and unsolved challenge for document forensics.”

from the abstract · picked out as the main claim by a classifier

Pith says

Pith has not reviewed this paper.

Get a Pith Review, $5

Reviews

Reviews by people

No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

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.

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-10-27 · no language-model review

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.97 · states limitation 0.30 · human participants 0.04 · controlled comparison 0.73 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.97 · mentions code or data availability 0.07

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v2). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
We present AIForge-Doc, the first dedicated benchmark targeting exclusively diffusion-model-based inpainting in financial and form documents with pixel-level annotation. contribution 1.00 0.91 0.08 asserted 1.00
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. gap 0.98 0.06 0.04 asserted 1.00
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. method 0.85 0.97 0.05 asserted 1.00
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. result 1.00 0.96 0.38 asserted 1.00
These results demonstrate that AIForge-Doc represents a qualitatively new and unsolved challenge for document forensics. interpretation 1.00 0.56 0.85 asserted 1.00

What kind of paper the classifier reports this is: dataset or benchmark 1.00 · evidence from observation or experiment 0.99

What was examined, and what was not

Sources read

  • arXiv listing abstract v2

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-10-27: 1 request, 4,683 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

How the literature uses it

2 arXiv papers cite this in 7 sentences

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers citing it · 5 sentences without a confident label

Uses its data or values 1 paper
  • We reuse the four source corpora and the $4,062$ forgery specifications of AIForge-Doc v1 [ref] verbatim: cord v2 [ref] (1,000 Indonesian receipts), WildReceipt [ref] (1,696 English receipts), SROIE [ref] (946 English receipts), and XFUND [ref] (420 multilingual forms in seven non-English languages).

    When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents · Source Datasets and Forgery Specifications · 0.99

Cites it as background 1 paper

Challenges and discussion

Know something about this paper? Leave a comment.

No comments yet.

Sign in to comment