# VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis

arXiv: https://arxiv.org/abs/2503.16195 · HTML: https://mlsanity.com/paper/2503.16195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 18 of 18)

- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Exploring Visual Prompts for Adapting Large-Scale Models](https://mlsanity.com/paper/2203.17274/) (2022)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [Instance-Conditioned GAN](https://mlsanity.com/paper/2109.05070/) (2021)
- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [Understanding and Improving Visual Prompting: A Label-Mapping Perspective](https://mlsanity.com/paper/2211.11635/) (2022)
- [Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning](https://mlsanity.com/paper/2102.12677/) (2021)
- [A General Approach to Adding Differential Privacy to Iterative Training Procedures](https://mlsanity.com/paper/1812.06210/) (2018)
- [Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources](https://mlsanity.com/paper/2007.08714/) (2020)
- [DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation](https://mlsanity.com/paper/2002.11603/) (2020)
- [Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence](https://mlsanity.com/paper/2111.01177/) (2021)
- [G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators](https://mlsanity.com/paper/1906.09338/) (2019)
- [Cross-modal Adversarial Reprogramming](https://mlsanity.com/paper/2102.07325/) (2021)
- [DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation](https://mlsanity.com/paper/2103.11109/) (2021)
- [PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning](https://mlsanity.com/paper/2106.04590/) (2021)
- [Hermite Polynomial Features for Private Data Generation](https://mlsanity.com/paper/2106.05042/) (2021)
- [Exploring the Benefits of Visual Prompting in Differential Privacy](https://mlsanity.com/paper/2303.12247/) (2023)
- [Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation](https://mlsanity.com/paper/2303.01687/) (2023)

## Abstract (arXiv)

Differentially private (DP) synthetic data has become the de facto standard for releasing sensitive data. However, many DP generative models suffer from the low utility of synthetic data, especially for high-resolution images. On the other hand, one of the emerging techniques in parameter efficient fine-tuning (PEFT) is visual prompting (VP), which allows well-trained existing models to be reused for the purpose of adapting to subsequent downstream tasks. In this work, we explore such a phenomenon in constructing captivating generative models with DP constraints. We show that VP in conjunction with DP-NTK, a DP generator that exploits the power of the neural tangent kernel (NTK) in training DP generative models, achieves a significant performance boost, particularly for high-resolution image datasets, with accuracy improving from 0.644±0.044 to 0.769. Lastly, we perform ablation studies on the effect of different parameters that influence the overall performance of VP-NTK. Our work demonstrates a promising step forward in improving the utility of DP synthetic data, particularly for high-resolution images.