Differential privacy promises to enable general data analytics while protecting individual
privacy, but existing differential privacy mechanisms do not support the wide variety of …

We present a rigorous methodology for auditing differentially private machine learning by
adding multiple carefully designed examples called canaries. We take a first principles …

The widespread acceptance of differential privacy has led to the publication of many
sophisticated algorithms for protecting privacy. However, due to the subtle nature of this …

Bug-fixes are widely used for predicting bugs or finding risky parts of software. However, a
bug-fix does not contain information about the change that initially introduced a bug. Such …

Dependent types allow us to express precisely what a function is intended to do. Recent
work on Quantitative Type Theory (QTT) extends dependent type systems with linearity, also …

In programming, some data acts as a resource (eg, file handles, channels) subject to usage
constraints. This poses a challenge to software correctness as most languages are agnostic …

Modern consumers increasingly embrace the personalization of services. Whether to
disclose private information to companies for the sake of receiving personalized service is …

We introduce the notion of a reproducible algorithm in the context of learning. A reproducible
learning algorithm is resilient to variations in its samples—with high probability, it returns the …

We present an approach to differentially private computation in which one does not scale up
the magnitude of noise for challenging queries, but rather scales down the contributions of …

Differential privacy provides a way to get useful information about sensitive data without
revealing much about any one individual. It enjoys many nice compositionality properties not …