Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for
recent advances in private deep learning. It provides a single privacy guarantee to all …

We consider how to design an anonymous data collection protocol that enforces compliance
rules. Imagine that each client contributes multiple data items (eg, votes, location crumbs, or …

Online data analytics with local privacy protection is widely adopted in real-world
applications. Despite numerous endeavors in this field, significant gaps in utility and …

In decentralized scenarios without fully trustable parties (eg, in mobile edge computing or
IoT environments), the shuffle model has recently emerged as a promising paradigm for …

In data-driven applications, preserving user privacy while enabling valuable computations
remains a critical challenge. Technologies like Differential Privacy (DP) have been pivotal in …

The shuffle model of differential privacy (DP) offers compelling privacy-utility trade-offs in
decentralized settings (eg, internet of things, mobile edge networks). Particularly, the multi …

Numerical vector aggregation plays a crucial role in privacy-sensitive applications, such as
distributed gradient estimation in federated learning and statistical analysis of key-value …

Personalized local differential privacy is a privacy protection mechanism that aims to
safeguard the privacy of data by using personalized approaches, while also providing …

Anonymous systems are susceptible to malicious activity. For instance, in anonymous
payment systems, users may engage in illicit practices like money laundering. Similarly …