# VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference

arXiv: https://arxiv.org/abs/2512.18853 · HTML: https://mlsanity.com/paper/2512.18853/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 75 references that are in the map.
- First posted on arXiv 21 Dec 2025.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [Factuality Challenges in the Era of Large Language Models](https://mlsanity.com/paper/2310.05189/) (2023)
- [MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection](https://mlsanity.com/paper/2112.08935/) (2021)
- [EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection](https://mlsanity.com/paper/2312.08883/) (2023)
- [Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want](https://mlsanity.com/paper/2403.20271/) (2024)
- [Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms](https://mlsanity.com/paper/2212.12678/) (2022)
- [The Perils & Promises of Fact-checking with Large Language Models](https://mlsanity.com/paper/2310.13549/) (2023)
- [Prompt Highlighter: Interactive Control for Multi-Modal LLMs](https://mlsanity.com/paper/2312.04302/) (2023)
- [How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?](https://mlsanity.com/paper/2407.17291/) (2024)
- [Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning](https://mlsanity.com/paper/2407.20174/) (2024)
- [MaLP: Manipulation Localization Using a Proactive Scheme](https://mlsanity.com/paper/2303.16976/) (2023)
- [VizLinter: A Linter and Fixer Framework for Data Visualization](https://mlsanity.com/paper/2108.10299/) (2021)
- [Misinformed by Visualization: What Do We Learn From Misinformative Visualizations?](https://mlsanity.com/paper/2204.09548/) (2022)
- [Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering](https://mlsanity.com/paper/2503.18172/) (2025)
- [AskChart: Universal Chart Understanding through Textual Enhancement](https://mlsanity.com/paper/2412.19146/) (2024)
- [VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network](https://mlsanity.com/paper/2009.03817/) (2020)
- ["I Came Across a Junk": Understanding Design Flaws of Data Visualization from the Public's Perspective](https://mlsanity.com/paper/2407.11497/) (2024)
- [VisImages: A Fine-Grained Expert-Annotated Visualization Dataset](https://mlsanity.com/paper/2007.04584/) (2020)
- [InvVis: Large-Scale Data Embedding for Invertible Visualization](https://mlsanity.com/paper/2307.16176/) (2023)
- [Why Change My Design: Explaining Poorly Constructed Visualization Designs with Explorable Explanations](https://mlsanity.com/paper/2309.01445/) (2023)
- [Truncating the Y-Axis: Threat or Menace?](https://mlsanity.com/paper/1907.02035/) (2019)
- [GeoLinter: A Linting Framework for Choropleth Maps](https://mlsanity.com/paper/2310.13707/) (2023)

## Built on by (most cited first, 3 of 3)

- [VeriLLMed: Interactive Visual Debugging of Medical Large Language Models with Knowledge Graphs](https://mlsanity.com/paper/2604.23356/) (2026)
- [SupplyNet: Supporting Visual Exploratory Learning in Supply Chain via Contextual Multi-Agent Simulation](https://mlsanity.com/paper/2606.24694/) (2026)
- [VizAnchor: Decoding Manipulation Intent from Tampering Visualizations via Dual-Anchor Reasoning](https://mlsanity.com/paper/2608.24535/) (2026)

## Abstract (arXiv)

The integrity of data visualizations is increasingly threatened by image editing techniques that enable subtle yet deceptive tampering. Through a formative study, we define this challenge and categorize tampering techniques into two primary types: data manipulation and visual encoding manipulation. To address this, we present VizDefender, a framework for tampering detection and analysis. The framework integrates two core components: 1) a semi-fragile watermark module that protects the visualization by embedding a location map to images, which allows for the precise localization of tampered regions while preserving visual quality, and 2) an intent analysis module that leverages Multimodal Large Language Models (MLLMs) to interpret manipulation, inferring the attacker's intent and misleading effects. Extensive evaluations and user studies demonstrate the effectiveness of our methods.