发表机构
School of Data Science and Engineering, East China Normal University; Division of Emerging Interdisciplinary Areas, The Hong Kong University of Science and Technology; School of Computer Science and Technology, East China Normal University（华东师范大学数据科学与工程学院; 香港科技大学新兴跨学科领域分部; 华东师范大学计算机科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出VizAnchor框架，通过双锚构建与VLM推理实现可视化操纵理解，含三个专用智能体，构建相关数据集，可准确定位篡改并生成忠实解释。
AI 中文摘要
数据可视化被广泛用于信息传达，但也易遭受故意篡改以诱导误导性解读。现有方法聚焦于定位篡改区域或恢复隐藏信息，却未解释可视化是如何被操纵的，以及产生的变化为何可能误导观众。本文提出VizAnchor，这是一个通过双锚证据构建和基于VLM的推理实现可视化操纵理解的框架。第一阶段，VizAnchor构建语义锚以恢复真实图表信息，以及空间锚以定位篡改区域。第二阶段，三个专用智能体解码操纵：误导者定位智能体分析四面板视觉提示以预测误导者信息；图表叙事重建智能体以原始图表和篡改图表为输入，重建各自的视觉叙事；最终，意图推理智能体整合视觉证据和误导者信息以推断误导意图。本文还构建了用于篡改定位的数据集和用于误导意图推理的数据集。评估显示，VizAnchor能准确定位篡改，并生成关于其操纵、误导者及误导意图的忠实解释。
英文摘要
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.
Comments39 pages
