Rethinking Utility in Differentially Private Visualization: A Channel-Centric Perspective
Authors
Jing Yang (University of North Carolina at Charlotte), Sarayu Pacca (University of North Carolina at Charlotte), Zhaocong Yang (University of North Carolina at Charlotte), Liyue Fan (University of North Carolina at Charlotte)
Presentation
- Session
- Can We Trust This Chart? (Asking for a Friend)
- Time
- Wednesday, Nov 11, 08:45 – 08:54 (US/Eastern) · session 08:00 – 09:30
- Location
- Hall America south
Keywords
Differential privacy, Visual channels, Privacy-preserving visualization, Visualization utility.
Abstract
Differential privacy (DP) is increasingly adopted to protect sensitive data in visualization, but understanding how privacy-induced noise affects visual representations remains fragmented. Prior work has examined the impact of DP noise on specific chart types, yet these findings are typically tied to particular chart types and evaluation settings, making it difficult to generalize across contexts. In parallel, visualization research has long established that visual channels, the visual properties of marks that encode data attributes, differ in perceptual effectiveness under noise-free conditions. However, these principles have not been systematically revisited under DP, where noise is deliberately introduced into the data to protect privacy. In this paper, we present a channel-centric perspective to reframe prior empirical and theoretical results. Our synthesis drawson prior findings to motivate a channel-read-mechanism hypothesis: the utility of DP visualizations may depend on the task-relevant reads made salient by visual channel configurations and DP mechanism choice jointly. Moreover, this perspective highlights the role of channel choice throughout the privacy-preserving visualization pipeline, from disclosure framing and DP algorithm design to utility evaluation and interpretation of noisy outputs. The synthesis also identifies gaps in the existing evaluation literature and highlights research opportunities for channel-aware DP visualization.
For Practitioners
Visualization researchers and practitioners developing privacy-preserving data analysis systems are the primary audience, including data scientists and engineers in organizations that release differentially private data. They can apply the channel-centric perspective to make more informed choices about visualization design, DP mechanism selection, and utility evaluation.