DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning

• URL: http://arxiv.org/abs/2604.02694v1
• Date: Fri, 03 Apr 2026 03:38:58 GMT
• Title: DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning
• Abstract summary: Existing forensic methods rely on visual cues and lack evidence-based reasoning to reveal subtle text manipulations.<n>We propose DocShield, the first unified framework formulating text-centric forgery analysis as a visual-logical co-reasoning problem.<n>Our dataset, model, and code will be publicly released.
• Score: 40.557106473604485
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly rely on visual cues and lack evidence-based reasoning to reveal subtle text manipulations. Detection, localization, and explanation are often treated as isolated tasks, limiting reliability and interpretability. To tackle these challenges, we propose DocShield, the first unified framework formulating text-centric forgery analysis as a visual-logical co-reasoning problem. At its core, a novel Cross-Cues-aware Chain of Thought (CCT) mechanism enables implicit agentic reasoning, iteratively cross-validating visual anomalies with textual semantics to produce consistent, evidence-grounded forensic analysis. We further introduce a Weighted Multi-Task Reward for GRPO-based optimization, aligning reasoning structure, spatial evidence, and authenticity prediction. Complementing the framework, we construct RealText-V1, a multilingual dataset of document-like text images with pixel-level manipulation masks and expert-level textual explanations. Extensive experiments show DocShield significantly outperforms existing methods, improving macro-average F1 by 41.4% over specialized frameworks and 23.4% over GPT-4o on T-IC13, with consistent gains on the challenging T-SROIE benchmark. Our dataset, model, and code will be publicly released.

Related papers

• Achieving Text-based Person Retrieval with Any Granularity [80.69427598925718]
  This paper introduces a new paradigm, Text-based Person Retrieval with Any Granularity.<n>We formalize a five-level granularity spectrum and construct UFine6926-MG, a high-quality multi-grained annotated dataset.<n>We then propose the Cross-modal Multi-grained Aligning and Matching framework.
  arXiv  Detail & Related papers  (2026-07-23T08:42:25Z)
• Beyond Detection: A Structure-Aware Framework for Scene Text Tracking [15.940149796254955]
  This paper formalizes this specific task as Scene Text Tracking.<n>We propose SymTrack, a unified detection-free framework with synergistic dual-branch design.<n>Considering lack of dedicated benchmarks for this task, we utilize three datasets from video text spotting to construct a benchmark with high-quality annotations.
  arXiv  Detail & Related papers  (2026-05-17T05:40:55Z)
• TextShield-R1: Reinforced Reasoning for Tampered Text Detection [48.66129052598456]
  TextShield-R1 is the first reinforcement learning based MLLM solution for tampered text detection and reasoning.<n>We introduce Forensic Continual Pre-training, an easy-to-hard curriculum that well prepares the MLLM for tampered text detection.<n>We also introduce the Text Forensics Reasoning (TFR) benchmark, comprising over 45k real and tampered images across 16 languages.
  arXiv  Detail & Related papers  (2026-02-23T13:26:18Z)
• LogicLens: Visual-Logical Co-Reasoning for Text-Centric Forgery Analysis [10.305807834419765]
  Text-centric forgeries pose a significant threat to societal security and information authenticity.<n>Current methods for text-centric forgery analysis are often limited to coarse-grained visual analysis.<n>We introduce LogicLens, a unified framework for Visual-Textual Co-reasoning.
  arXiv  Detail & Related papers  (2025-12-25T03:02:27Z)
• CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection [16.113113157328662]
  Existing zero-shot detection paradigms often exhibit significant deficiencies.<n>We introduce textbfCAMF, a novel architecture using multiple LLM-based agents.<n>This structured collaborative-adversarial process enables a deep analysis of subtle, cross-dimensional textual incongruities indicative of non-human origin.
  arXiv  Detail & Related papers  (2025-08-16T06:25:27Z)
• From Prediction to Explanation: Multimodal, Explainable, and Interactive Deepfake Detection Framework for Non-Expert Users [21.627851460651968]
  We present DF-P2E (Deepfake: Prediction to Explanation), a novel framework that integrates visual, semantic, and narrative layers of explanation to make deepfake detection interpretable and accessible.<n>We instantiate and evaluate the framework on the DF40 benchmark, the most diverse deepfake dataset to date.<n> Experiments demonstrate that our system achieves competitive detection performance while providing high-quality explanations aligned with Grad-CAM activations.
  arXiv  Detail & Related papers  (2025-08-11T03:55:47Z)
• Structured Attention Matters to Multimodal LLMs in Document Understanding [52.37530640460363]
  We investigate how input format influences document comprehension performance.<n>We discover that raw OCR text often impairs rather than improves MLLMs' performance.<n>We propose a novel structure-preserving approach that encodes document elements using the LaTex paradigm.
  arXiv  Detail & Related papers  (2025-06-19T07:16:18Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision [61.186488081379]
  We propose TextFormer, a query-based end-to-end text spotter with Transformer architecture. TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multi-task modeling. It allows for mutual training and optimization of classification, segmentation, and recognition branches, resulting in deeper feature sharing.
  arXiv  Detail & Related papers  (2023-06-06T03:37:41Z)

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.