用视觉提示提升差分隐私图像合成质量，高分辨率数据效果显著。
VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis
- 结合视觉提示与差分隐私神经正切核生成器，提升模型效率。
- 高分辨率图像合成准确率从0.644提升至0.769。
- 适合关注隐私保护图像生成的研究者与应用开发者。
差分隐私（DP）合成数据已成为敏感数据发布的主要方式。然而，许多DP生成模型生成的合成数据实用性较低，尤其在高分辨率图像场景下表现不佳。另一方面，参数高效微调（PEFT）中新兴的视觉提示（VP）技术，可使预训练模型有效适配下游任务。本文探索在DP约束下使用视觉提示构建高质量生成模型的潜力。结果表明，将视觉提示与基于神经正切核（NTK）的差分隐私生成器（DP-NTK）结合，在高分辨率图像数据集上实现显著性能提升，合成图像准确率由0.644±0.044提升至0.769。最后，我们对影响整体性能的关键参数进行了消融分析。本工作为提升高分辨率图像差分隐私合成数据的实用性提供了有前景的方向。
原文摘要 · Abstract (English)
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$\pm$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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。