Related papers: Tumult Analytics: a robust, easy-to-use, scalable,…
Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for discrete attributes. Differential privacy, which provides a more…
AI intensive systems that operate upon user data face the challenge of balancing data utility with privacy concerns. We propose the idea and present the prototype of an open-source tool called Privacy Utility Trade-off (PUT) Workbench which…
In modern distributed computing applications, such as federated learning and AIoT systems, protecting privacy is crucial to prevent adversarial parties from colluding to steal others' private information. However, guaranteeing the utility…
Preserving privacy of users is a key requirement of web-scale analytics and reporting applications, and has witnessed a renewed focus in light of recent data breaches and new regulations such as GDPR. We focus on the problem of computing…
Pseudonymisation provides the means to reduce the privacy impact of monitoring, auditing, intrusion detection, and data collection in general on individual subjects. Its application on data records, especially in an environment with…
Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function. Bounding such sensitivity is often a prohibitively…
Differential privacy is a statistical definition of privacy that has attracted the interest of both academia and industry. Its formulations are easy to understand, but the differential privacy of databases is complicated to determine. One…
With the growing demand for synthetic data to address contemporary issues in machine learning, such as data scarcity, data fairness, and data privacy, having robust tools for assessing the utility and potential privacy risks of such data…
Third-party analysis on private records is becoming increasingly important due to the widespread data collection for various analysis purposes. However, the data in its original form often contains sensitive information about individuals,…
Open data plays a fundamental role in the 21th century by stimulating economic growth and by enabling more transparent and inclusive societies. However, it is always difficult to create new high-quality datasets with the required privacy…
The U.S. Decennial Census serves as the foundation for many high-profile policy decision-making processes, including federal funding allocation and redistricting. In 2020, the Census Bureau adopted differential privacy to protect the…
State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarantees remains challenging. We introduce a Gaussian Differential Privacy (GDP)-based auditing…
The average treatment effect (ATE) is widely used to evaluate the effectiveness of drugs and other medical interventions. In safety-critical applications like medicine, reliable inferences about the ATE typically require valid uncertainty…
Survival analysis studies the statistical properties of the time until an event of interest occurs. It has been commonly used to study the effectiveness of medical treatments or the lifespan of a population. However, survival analysis can…
In this work, we study high-dimensional mean estimation under user-level differential privacy, and design an $(\varepsilon,\delta)$-differentially private mechanism using as few users as possible. In particular, we provide a nearly optimal…
Collecting and analyzing massive data generated from smart devices have become increasingly pervasive in crowdsensing, which are the building blocks for data-driven decision-making. However, extensive statistics and analysis of such data…
This chapter is meant to be part of the book "Differential Privacy for Artificial Intelligence Applications." We give an introduction to the most important property of differential privacy -- composition: running multiple independent…
Differential privacy (DP) is a rigorous notion of data privacy, used for private statistics. The canonical algorithm for differentially private mean estimation is to first clip the samples to a bounded range and then add noise to their…
With low-cost computing devices, improved sensor technology, and the proliferation of data-driven algorithms, we have more data than we know what to do with. In transportation, we are seeing a surge in spatiotemporal data collection. At the…
Motivated by the 2020 US Census products, this paper extends differential privacy (DP) to address the joint release of DP outputs and nonprivate statistics, referred to as invariant. Our framework, Semi-DP, redefines adjacency by focusing…