Large Scale Transfer Learning for Differentially Private Image Classification. (arXiv:2205.02973v1 [cs.LG])

Web: http://arxiv.org/abs/2205.02973

Differential Privacy (DP) provides a formal framework for training machine
learning models with individual example level privacy. Training models with DP
protects the model against leakage of sensitive data in a potentially
adversarial setting. In the field of deep learning, Differentially Private
Stochastic Gradient Descent (DP-SGD) has emerged as a popular private training
algorithm. Private training using DP-SGD protects against leakage by injecting
noise into individual example gradients, such that the trained model weights
become nearly independent of the use …

arxiv classification image learning scale transfer transfer learning