Anonymization is a practical solution for preserving user's privacy in data publishing. Data
owners such as hospitals, banks, social network (SN) service providers, and insurance …

Context: Advancements in machine learning (ML) lead to a shift from the traditional view of
software development, where algorithms are hard-coded by humans, to ML systems …

Synthetic health data have the potential to mitigate privacy concerns in supporting
biomedical research and healthcare applications. Modern approaches for data generation …

Limited data access is a longstanding barrier to data-driven research and development in
the networked systems community. In this work, we explore if and how generative …

This paper describes the deployment of a large-scale study designed to measure human
interactions across a variety of communication channels, with high temporal resolution and …

Federated learning (FL) is an emerging distributed learning paradigm with default client
privacy because clients can keep sensitive data on their devices and only share local …

We examine a very large-scale data set of more than 30 billion call records made by 25
million cell phone users across all 50 states of the US and attempt to determine to what …

Ensuring the usefulness of electronic data sources while providing necessary privacy
guarantees is an important unsolved problem. This problem drives the need for an analytical …

Several anonymization techniques, such as generalization and bucketization, have been
designed for privacy preserving microdata publishing. Recent work has shown that …

Accurately learning from user data while providing quantifiable privacy guarantees provides
an opportunity to build better ML models while maintaining user trust. This paper presents a …