PATE-TripleGAN: Privacy-Preserving Image Synthesis with Gaussian Differential Privacy

arXiv:2404.12730v1 Announce Type: cross
Abstract: Conditional Generative Adversarial Networks (CGANs) exhibit significant potential in supervised learning model training by virtue of their ability to generate realistic labeled images. However, numerous studies have indicated the privacy leakage risk in CGANs models. The solution DPCGAN, incorporating the differential privacy framework, faces challenges such as heavy reliance on labeled data for model training and potential disruptions to original gradient information due to excessive gradient clipping, making it difficult to ensure model accuracy. To …

abstract adversarial arxiv challenges cs.cr cs.cv cs.lg differential differential privacy framework generate generative generative adversarial networks however image images networks privacy risk solution studies supervised learning synthesis training type