Beyond Natural Images: Rethinking AI-Generated Image Detection in Documents

• URL: http://arxiv.org/abs/2609.14352v1
• Date: Sun, 13 Sep 2026 07:26:45 GMT
• Title: Beyond Natural Images: Rethinking AI-Generated Image Detection in Documents
• Abstract summary: Existing evaluations mainly focus on natural images, leaving AI-generated document images largely underexplored.<n>In this paper, we first construct a controlled diagnostic benchmark, AIGDoc-Pilot, and reveal that existing detectors suffer substantial performance degradation on AI-generated document images.<n>Motivated by these findings, we construct AIGDoc, a larger document-centric dataset containing diverse real-world documents and AI-generated counterparts.
• Score: 10.557290199192074
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI-generated image detection has attracted increasing attention, but existing evaluations mainly focus on natural images, leaving AI-generated document images largely underexplored. This omission is concerning because documents often appear in sensitive real-world scenarios, such as invoices, expense reports, certificates, and medical records. In this paper, we first construct a controlled diagnostic benchmark, AIGDoc-Pilot, and reveal that existing detectors suffer substantial performance degradation on AI-generated document images, with the mean AUC dropping by more than 7%. Based on this, we further reveal two document-specific properties behind this gap: generation artifacts exhibit strong spatial inconsistency across local regions, and text density significantly affects real-synthetic separability, where text-dense regions offer stronger discriminative evidence. Motivated by these findings, we construct AIGDoc, a larger document-centric dataset containing diverse real-world documents and AI-generated counterparts produced by multiple advanced generation and editing models. Extensive experiments on AIGDoc demonstrate that existing detectors still struggle to reliably identify AI-generated documents, while document-based training partially narrows the gap. Together, these results offer valuable insights for developing dependable and generalizable detectors in document-centric scenarios. The code and datasets will be made publicly available upon acceptance of the paper.

Related papers

• GenShield: Unified Detection and Artifact Correction for AI-Generated Images [65.11434977803509]
  GenShield is a framework that performs AIGI detection and artifact correction in a closed loop from diagnosis to restoration.<n>A high-quality dataset with large-scale artifact-restored'' pairs is constructed alongside a unified evaluation pipeline.
  arXiv  Detail & Related papers  (2026-05-15T16:06:20Z)
• Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection [95.08316274158165]
  X-AIGD provides pixel-level, categorized annotations of perceptual artifacts, spanning low-level distortions, high-level semantics, and cognitive-level counterfactuals.<n>Existing AIGI detectors demonstrate negligible reliance on perceptual artifacts, even at the most basic distortion level.<n>Explicitly aligning model attention with artifact regions can increase the interpretability and generalization of detectors.
  arXiv  Detail & Related papers  (2026-01-27T10:09:17Z)
• Can Generative Models Actually Forge Realistic Identity Documents? [51.56484100374058]
  Open-source and publicly accessible generative models can produce identity document forgeries.<n>Risk of generative identity document deepfakes achieving forensic-level authenticity may be overestimated.
  arXiv  Detail & Related papers  (2025-12-25T00:56:50Z)
• HybriDLA: Hybrid Generation for Document Layout Analysis [40.47982474843359]
  HybriDLA is a novel generative framework that unifies diffusion and autoregressive decoding within a single layer.<n>This architecture elevates performance to 83.5% mean Average Precision (mAP)
  arXiv  Detail & Related papers  (2025-11-25T04:53:47Z)
• Open Multimodal Retrieval-Augmented Factual Image Generation [86.34546873830152]
  We introduce ORIG, an agentic open multimodal retrieval-augmented framework for Factual Image Generation (FIG)<n> ORIG iteratively retrieves and filters multimodal evidence from the web and incrementally integrates the refined knowledge into enriched prompts to guide generation.<n>Experiments demonstrate that ORIG substantially improves factual consistency and overall image quality over strong baselines.
  arXiv  Detail & Related papers  (2025-10-26T04:13:31Z)
• Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images [96.43608872116347]
  AnomReason is a large-scale benchmark with structured annotations as quadruple textbfAnomAgent<n>AnomReason and AnomAgent serve as a foundation for measuring and improving the semantic plausibility of AI-generated images.
  arXiv  Detail & Related papers  (2025-10-11T14:09:24Z)
• EdgeDoc: Hybrid CNN-Transformer Model for Accurate Forgery Detection and Localization in ID Documents [6.690084812573466]
  EdgeDoc is a novel approach for the detection and localization of document forgeries.<n>Our architecture combines a lightweight convolutional transformer with auxiliary noiseprint features extracted from the images.
  arXiv  Detail & Related papers  (2025-08-22T10:45:14Z)
• DvD: Unleashing a Generative Paradigm for Document Dewarping via Coordinates-based Diffusion Model [36.509036144494495]
  We propose DvD, the first generative model to tackle document Dewarping via a Diffusion framework.<n>To be specific, DvD introduces a coordinate-level denoising instead of typical pixel-level denoising, generating a mapping for deformation rectification.<n>We present AnyPhotoDoc6300, a rigorously designed large-scale document dewarping benchmark comprising 6,300 real image pairs.
  arXiv  Detail & Related papers  (2025-05-28T05:05:51Z)
• DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures [24.76258692552673]
  We present DocAligner, a novel method that streamlines the manual annotation process to a simple step of taking pictures. It achieves this by establishing dense correspondence between photographic document images and their clean counterparts. Considering the distinctive characteristics of document images, DocAligner incorporates several innovative features.
  arXiv  Detail & Related papers  (2023-06-09T08:29:15Z)
• SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation [15.953725529361874]
  Document layout analysis is a known problem to the documents research community. With growing internet connectivity to personal life, an enormous amount of documents had been available in the public domain. We address this challenge using self-supervision and unlike, the few existing self-supervised document segmentation approaches.
  arXiv  Detail & Related papers  (2023-05-01T12:47:55Z)
• DocScanner: Robust Document Image Rectification with Progressive Learning [162.03694280524084]
  This work presents DocScanner, a new deep network architecture for document image rectification. DocScanner maintains a single estimate of the rectified image, which is progressively corrected with a recurrent architecture. The iterative refinements make DocScanner converge to a robust and superior performance, and the lightweight recurrent architecture ensures the running efficiency.
  arXiv  Detail & Related papers  (2021-10-28T09:15:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.