Safeguarding privacy in sensitive training data is paramount, particularly in the context of generative modeling. This is done through either differentially private stochastic gradient descent, or with a differentially private metric for training models or generators. In this paper, we introduce a novel differentially private generative modeling approach based on parameter-free gradient flows in the space of probability measures. The proposed algorithm is a new discretized flow which operates through a particle scheme, utilizing drift derived from the sliced Wasserstein distance and computed in a private manner. Our experiments show that compared to a generator-based model, our proposed model can generate higher-fidelity data at a low privacy budget, offering a viable alternative to generator-based approaches.

翻译：保护敏感训练数据中的隐私至关重要，尤其是在生成建模领域。这可以通过差分隐私随机梯度下降，或通过用于训练模型或生成器的差分隐私度量来实现。本文提出了一种新颖的差分隐私生成建模方法，该方法基于概率测度空间中的无参数梯度流。所提出算法是一种新的离散化流，通过粒子方案运行，利用从切片Wasserstein距离导出的漂移，并以隐私方式计算。实验表明，与基于生成器的模型相比，我们的模型能在低隐私预算下生成更高质量的数据，为基于生成器的方法提供了可行的替代方案。