Related papers: Compressive Sensing Approaches for Sparse Distribu…
Differentially private (DP) mechanisms have been deployed in a variety of high-impact social settings (perhaps most notably by the U.S. Census). Since all DP mechanisms involve adding noise to results of statistical queries, they are…
We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training…
Non-interactive Local Differential Privacy (LDP) requires data analysts to collect data from users through noisy channel at once. In this paper, we extend the frontiers of Non-interactive LDP learning and estimation from several aspects.…
Distributed data analysis is a large and growing field driven by a massive proliferation of user devices, and by privacy concerns surrounding the centralised storage of data. We consider two \emph{adaptive} algorithms for estimating one…
Local differential privacy has become the gold-standard of privacy literature for gathering or releasing sensitive individual data points in a privacy-preserving manner. However, locally differential data can twist the probability density…
Many resource allocation problems can be formulated as an optimization problem whose constraints contain sensitive information about participating users. This paper concerns solving this kind of optimization problem in a distributed manner…
The private collection of multiple statistics from a population is a fundamental statistical problem. One possible approach to realize this is to rely on the local model of differential privacy (LDP). Numerous LDP protocols have been…
Joint distribution estimation of a dataset under differential privacy is a fundamental problem for many privacy-focused applications, such as query answering, machine learning tasks and synthetic data generation. In this work, we examine…
This paper addresses the problem of differentially private distributed optimization under limited communication, where each agent aims to keep their cost function private while minimizing the sum of all agents' cost functions. In response,…
Local Differential Privacy (LDP) is popularly used in practice for privacy-preserving data collection. Although existing LDP protocols offer high utility for large user populations (100,000 or more users), they perform poorly in scenarios…
Local differential privacy (LDP) has recently become a popular privacy-preserving data collection technique protecting users' privacy. The main problem of data stream collection under LDP is the poor utility due to multi-item collection…
Data privacy and decentralised data collection has become more and more popular in recent years. In order to solve issues with privacy, communication bandwidth and learning from spatio-temporal data, we will propose two efficient models…
Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…
The emergence and evolution of Local Differential Privacy (LDP) and its various adaptations play a pivotal role in tackling privacy issues related to the vast amounts of data generated by intelligent devices, which are crucial for…
We investigate how to optimally design local differential privacy (LDP) mechanisms that reduce data unfairness and thereby improve fairness in downstream classification. We first derive a closed-form optimal mechanism for binary sensitive…
In this work, we give efficient algorithms for privately estimating a Gaussian distribution in both pure and approximate differential privacy (DP) models with optimal dependence on the dimension in the sample complexity. In the pure DP…
In this paper we study the problem of estimating the unknown mean $\theta$ of a unit variance Gaussian distribution in a locally differentially private (LDP) way. In the high-privacy regime ($\epsilon\le 1$), we identify an optimal privacy…
Confidence intervals are a fundamental tool for quantifying the uncertainty of parameters of interest. With the increase of data privacy awareness, developing a private version of confidence intervals has gained growing attention from both…
Privacy is crucial in many applications of machine learning. Legal, ethical and societal issues restrict the sharing of sensitive data making it difficult to learn from datasets that are partitioned between many parties. One important…
Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more…