Deep learning sits at the forefront of many on-going advances in a variety of learning tasks.
Despite its supremacy in accuracy under benign environments, Deep learning suffers from …

Data is the key factor to drive the development of machine learning (ML) during the past
decade. However, high-quality data, in particular labeled data, is often hard and expensive …

In recent years, the research community has increasingly focused on understanding the
security and privacy challenges posed by deep learning models. However, the security …

Previous studies have found that an adversary attacker can often infer unintended input
information from intermediate-layer features. We study the possibility of preventing such …

Adversarial learning is commonly used to extract latent data representations which are
expressive to predict the target attribute but indistinguishable in the privacy attribute …

Machine learning (ML) models have been deployed for high-stakes applications, eg,
healthcare and criminal justice. Prior work has shown that ML models are vulnerable to …

An important problem in deep learning is the privacy and security of neural networks (NNs).
Both aspects have long been considered separately. To date, it is still poorly understood …

Adversarial examples that fool machine learning models, particularly deep neural networks,
have been a topic of intense research interest, with attacks and defenses being developed …

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

Deep learning is data-hungry, and generally its performance highly depends on the amount
of training data. Multiple parties can obtain better models by sharing their data and train …