Deep Learning has recently become hugely popular in machine learning for its ability to
solve end-to-end learning systems, in which the features and the classifiers are learned …

Deep neural networks (DNNs) have recently been widely adopted in various applications,
and such success is largely due to a combination of algorithmic breakthroughs, computation …

A new collaborative learning, called split learning, was recently introduced, aiming to protect
user data privacy without revealing raw input data to a server. It collaboratively runs a deep …

The unprecedented success of deep learning is largely dependent on the availability of
massive amount of training data. In many cases, these data are crowd-sourced and may …

Recent success of deep neural networks (DNNs) hinges on the availability of large-scale
dataset; however, training on such dataset often poses privacy risks for sensitive training …

Nowadays, deep learning has many applications in our daily life such as self-driving,
product recommendation, advertisements and healthcare. In the training phase, deep …

The prevalence of deep learning has drawn attention to the privacy protection of sensitive
data. Various privacy threats have been presented, where an adversary can steal model …

Deep learning based on artificial neural networks is a very popular approach to modeling,
classifying, and recognizing complex data such as images, speech, and text. The …

By learning generative models of semantic-rich data distributions from samples, generative
adversarial network (GAN) has recently attracted intensive research interests due to its …

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve
differential privacy in deep neural networks, with provable robustness against adversarial …