Differential Privacy Data Synthesis Method Based on Latent Diffusion Model
The widespread application of data sharing and publication in the socio-economic domain drives scientific progress and societal development.However,issues related to copyright and privacy,especially concerning personal data,remain critical chal-lenges.Differential privacy data synthesis has emerged as an effective means of protecting data privacy,where data holders can re-lease synthetic data instead of real data,thereby enhancing data utility and availability while preserving privacy.In response to the limited usability of existing differential privacy generation models,this paper proposes a two-stage differential privacy generation model based on the latent space diffusion approach.Firstly,the differential privacy-aware information compression is performed on the original image,and it is projected from the pixel space to the latent space to obtain the desensitized latent vector represen-tation of the original sensitive data.The latent vector is then fed into a diffusion model to gradually transform into a prior distri-bution and sampled through a denoising process.Experimental results based on the MNIST and Fashion MNIST datasets demon-strate that the proposed model exhibits significant improvements in terms of Frechet inception distance(FID)and downstream task accuracy compared to state-of-the-art models like DP-Sinkhorn.
万方数据
维普
