VizAnchor: Decoding Manipulation Intent from Tampering Visualizations via Dual-Anchor Reasoning

• URL: http://arxiv.org/abs/2608.24535v1
• Date: Tue, 25 Aug 2026 13:20:27 GMT
• Title: VizAnchor: Decoding Manipulation Intent from Tampering Visualizations via Dual-Anchor Reasoning
• Abstract summary: VizAnchor is a framework for visualization manipulation understanding.<n>It recovers authentic chart information and localizes tampered regions.<n>It produces faithful explanations of their manipulation, misleaders, and misleading intents.
• Score: 29.562339801344375
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Data visualizations are widely used for communicating information, but they are also vulnerable to intentional manipulations that induce misleading interpretations. Existing methods focus on locating tampered regions or recovering hidden information, without explaining how the visualization has been manipulated or why the resulting changes may mislead viewers. We propose \textbf{VizAnchor}, a framework for visualization manipulation understanding through dual-anchor evidence construction and VLM-based reasoning. In the first stage, VizAnchor constructs a semantic anchor to recover authentic chart information and a spatial anchor to localize tampered regions. In the second stage, three specialized agents decode the manipulation. The misleader grounding agent analyzes a four-panel visual prompt to predict the misleader information. The chart narrative reconstruction agent takes the original and tampered charts as inputs and reconstructs their respective visual narratives. Finally, the intent inferring agent integrates the visual evidence and misleader information to infer the misleading intent. We further construct a dataset for tampering localization and a dataset for misleading intent inferring. Evaluation shows that VizAnchor accurately localizes manipulations and produces faithful explanations of their manipulation, misleaders, and misleading intents.

Related papers

• Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking [53.08526613328243]
  Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations.<n>We build on text-to-image diffusion models to exploit the rich semantic knowledge encoded in pretrained models.<n>Our method Diff-Tracking is composed of two main components: an initial prompt learner and an online prompt updater.
  arXiv  Detail & Related papers  (2026-05-26T12:26:56Z)
• What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews [31.373823254968315]
  Even when factually correct, social-media news previews can induce interpretation drift.<n>This covert harm is harder to detect than explicit misinformation yet remains underexplored.<n>We develop a multi-stage pipeline that disentangles and simulates preview-based versus context-based understanding.
  arXiv  Detail & Related papers  (2026-01-09T06:29:19Z)
• VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference [53.31458914370742]
  VizDefender is a framework for tampering detection and analysis.<n>The framework integrates two core components: 1) a semi-fragile watermark module that protects the visualization by embedding a location map to images, and 2) an intent analysis module that leverages Multimodal Large Language Models (MLLMs) to interpret manipulation.
  arXiv  Detail & Related papers  (2025-12-21T18:44:03Z)
• Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations [56.816929931908824]
  We pioneer the detection of semantically-coordinated manipulations in multimodal data.<n>We propose a Retrieval-Augmented Manipulation Detection and Grounding (RamDG) framework.<n>Our framework significantly outperforms existing methods, achieving 2.06% higher detection accuracy on SAMM compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-09-16T04:18:48Z)
• The Perils of Chart Deception: How Misleading Visualizations Affect Vision-Language Models [11.500090488046899]
  Vision-Language Models (VLMs) are increasingly used to interpret visualizations, especially by non-expert users.<n>This study analyzes over 16,000 responses from ten different models across eight distinct types of misleading chart designs.<n>Our findings highlight the need for robust safeguards in VLMs against visual misinformation.
  arXiv  Detail & Related papers  (2025-08-13T11:11:18Z)
• Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models [65.23999399834638]
  We introduce DeceptionDecoded, a benchmark of 12,000 image-caption pairs grounded in trustworthy reference articles.<n>The dataset captures both misleading and non-misleading cases, spanning manipulations across visual and textual modalities.<n>It supports three intent-centric tasks: misleading intent detection, misleading source attribution, and creator desire inference.
  arXiv  Detail & Related papers  (2025-05-21T13:14:32Z)
• Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning [56.65891462413187]
  We propose a progressive semantic-guided vision transformer for zero-shot learning (dubbed ZSLViT) ZSLViT first introduces semantic-embedded token learning to improve the visual-semantic correspondences via semantic enhancement. Then, we fuse low semantic-visual correspondence visual tokens to discard the semantic-unrelated visual information for visual enhancement.
  arXiv  Detail & Related papers  (2024-04-11T12:59:38Z)
• Exploring Saliency Bias in Manipulation Detection [2.156234249946792]
  Social media-fuelled explosion of fake news and misinformation supported by tampered images has led to growth in the development of models and datasets for image manipulation detection.<n>Existing detection methods mostly treat media objects in isolation, without considering the impact of specific manipulations on viewer perception.<n>We propose a framework to analyze the trends of visual and semantic saliency in popular image manipulation datasets and their impact on detection.
  arXiv  Detail & Related papers  (2024-02-12T00:08:51Z)
• Spatio-Temporal Graph for Video Captioning with Knowledge Distillation [50.034189314258356]
  We propose a graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid correlations caused by the variable number of objects, we propose an object-aware knowledge distillation mechanism.
  arXiv  Detail & Related papers  (2020-03-31T03:58:11Z)

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.