Differentially Private Paired Table-Image Multimodal Synthesis
cs.CR, cs.AI, cs.CV
Submitted: 2026-09-01
Updated: 2026-09-01
Code: https://github.com/KaiChen9909/TabImage_Syn
Terminology
Sources
- Differentially Private Diffusion Models
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
- Differentially Private Diffusion Models Generate Useful Synthetic Images
- DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis
- Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- On Differentially Private 3D Medical Image Synthesis with Controllable Latent Diffusion Models
- Method for Generating Synthetic Data Combining Chest Radiography Images with Tabular Clinical Information Using Dual Generative Models
- From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Benchmarking Differentially Private Synthetic Data Generation Algorithms
- Differentially Private Synthetic Data via Foundation Model APIs 1: Images
- MetaVoxel: Joint Diffusion Modeling of Imaging and Clinical Metadata
- New Oracle-Efficient Algorithms for Private Synthetic Data Release
- AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data
- Subsampled R'enyi Differential Privacy and Analytical Moments Accountant
- Differentially Private Generative Adversarial Network
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs