Abstract Machine Learning (ML) models are ubiquitous in real-world applications and are a
constant focus of research. Modern ML models have become more complex, deeper, and …

Modern cyber physical systems (CPSs) has widely being used in our daily lives because of
development of information and communication technologies (ICT). With the provision of …

Privacy-preserving data publishing is an important problem that has been the focus of
extensive study. The state-of-the-art solution for this problem is differential privacy, which …

Differential privacy is an essential and prevalent privacy model that has been widely
explored in recent decades. This survey provides a comprehensive and structured overview …

We propose a general approach for differentially private synthetic data generation, that
consists of three steps:(1) select a collection of low-dimensional marginals,(2) measure …

High-dimensional crowdsourced data collected from numerous users produces rich
knowledge about our society; however, it also brings unprecedented privacy threats to the …

With powerful parallel computing GPUs and massive user data, neural-network-based deep
learning can well exert its strong power in problem modeling and solving, and has archived …

In differential privacy (DP), a challenging problem is to generate synthetic datasets that
efficiently capture the useful information in the private data. The synthetic dataset enables …

Given a set D of tuples defined on a domain Omega, we study differentially private
algorithms for constructing a histogram over Omega to approximate the tuple distribution in …

Many privacy mechanisms reveal high-level information about a data distribution through
noisy measurements. It is common to use this information to estimate the answers to new …