VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference
This addresses the threat of deceptive image editing in visualizations, which is an incremental improvement for data integrity and security domains.
The paper tackles the problem of detecting tampering in data visualizations by introducing VizDefender, a framework that localizes tampered regions using watermarks and infers attacker intent with MLLMs, achieving effective results in evaluations and user studies.
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.