VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference

TL;DR

VizDefender is a framework that detects, localizes, and interprets tampering in data visualizations by combining watermarking techniques with multimodal language models to ensure integrity and understand attacker intent.

Contribution

This paper introduces VizDefender, a novel system integrating semi-fragile watermarking and multimodal language models for visualization tampering detection and analysis.

Findings

Effective tampering localization with minimal visual quality loss

Accurate inference of manipulation intent using MLLMs

Successful detection in diverse visualization scenarios

Abstract

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.