BAIT: Visual-illusion-inspired Privacy Preservation for Mobile Data Visualization

2026-01-26

AI Summary

This work addresses the vulnerability of mobile data visualizations to shoulder-surfing attacks, where existing approaches struggle to balance privacy protection with visual interpretability. Inspired by visual illusions, the study introduces BAIT—a novel framework that integrates human visual perception modeling into privacy-preserving design. BAIT automatically generates a decoy layer over the original visualization by modulating multi-channel visual variables—including shape, position, color, and spatial frequency—such that nearby authorized users can accurately interpret the underlying data, while distant observers are deliberately misled. By coupling a perceptual model with an optimization algorithm, the method enables viewing-distance–adaptive privacy protection. Two user studies, conducted in both controlled laboratory and real-world settings, demonstrate that BAIT effectively mitigates shoulder-surfing threats while significantly preserving the visual experience for legitimate users.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Data Mining & Knowledge Management: Data Visualization & Summarization

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Web Mining and Content Analysis: Web data visualization

Abstract

With the prevalence of mobile data visualizations, there have been growing concerns about their privacy risks, especially shoulder surfing attacks. Inspired by prior research on visual illusion, we propose BAIT, a novel approach to automatically generate privacy-preserving visualizations by stacking a decoy visualization over a given visualization. It allows visualization owners at proximity to clearly discern the original visualization and makes shoulder surfers at a distance be misled by the decoy visualization, by adjusting different visual channels of a decoy visualization (e.g., shape, position, tilt, size, color and spatial frequency). We explicitly model human perception effect at different viewing distances to optimize the decoy visualization design. Privacy-preserving examples and two in-depth user studies demonstrate the effectiveness of BAIT in both controlled lab study and real-world scenarios.

Problem

• privacy preservation
• mobile data visualization
• shoulder surfing
• visual illusion
• decoy visualization

Innovation

• visual illusion
• privacy-preserving visualization
• shoulder surfing
• human perception modeling
• decoy visualization