Differentially Private Generative Adversarial Networks with Model Inversion
원문 초록
To protect sensitive data in training a Generative Adversarial Network (GAN), the standard approach is to use differentially private (DP) stochastic gradient descent method in which controlled noise is added to the gradients. The quality of the output synthetic samples can be adversely affected and the training of the network may not even converge in the presence of these noises. We propose Differentially Private Model Inversion (DPMI) method where the private data is first mapped to the latent space via a public generator, followed by a lower-dimensional DP-GAN with better convergent properties. Experimental results on standard datasets CIFAR10 and SVHN as well as on a facial landmark dataset for Autism screening show that our approach outperforms the standard DP-GAN method based on Inception Score, Fr\'echet Inception Distance, and classification accuracy under the same privacy guarantee.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TabularQGAN: A Quantum Generative Model for Tabular Data
Synthesis of Ventilator Dyssynchrony Waveforms using a Hybrid Generative Model and a Lung Model
TabPFN: One Model to Rule Them All?
Making Language Model a Hierarchical Classifier and Generator
Implementing Adaptations for Vision AutoRegressive Model
Graph World Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.