SOURCE-LINKED INTELLIGENCE

Differentially Private Paired Table-Image Multimodal Synthesis

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Differentially private (DP) synthesis has been extensively studied for tabular and image data separately, yet many real-world datasets contain images paired with multivariate tabular records. Synthesizing such data is particularly challenging under DP, as the two modalities favor different private learning mechanisms while their dependence must also be preserved. To address this challenge, we propose DP-TabImage, a modality-specialized framework for private paired synthesis. DP-TabImage instantiates the factorization $p(x,y)=p_T(y)p_I(x\;|\;y)$ using a private Probabilistic Graphical Model for

Read original source ↗ Open in workspace

recordType

paper

region

Global