Exploring the Privacy--Size Tradeoff for Differentially Private Self-Attentive Variational Autoencoders
cs.LG, cs.CE, cs.CR
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation
- Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis
- Benchmarking Differentially Private Tabular Data Synthesis
- The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets
- Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility
- TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data
- A self-attention-based differentially private tabular GAN with high data utility
- Synthetic Data -- Anonymisation Groundhog Day
- Benchmarking Differentially Private Synthetic Data Generation Algorithms
- Membership Inference Attacks against Synthetic Data through Overfitting Detection
- The DCR Delusion: Measuring the Privacy Risk of Synthetic Data
- PATE-TabTransGAN: Differentially Private Synthetic Tabular Data Generation via Transformer-Based Student Discrimination
- DP-TLDM: Differentially Private Tabular Latent Diffusion Model
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis