Related papers: Optimal Accuracy-Privacy Trade-Off for Secure Mult…

We study privacy-utility trade-offs where users share privacy-correlated useful information with a service provider to obtain some utility. The service provider is adversarial in the sense that it can infer the users' private information…

In this work, fundamental limits and optimal mechanisms of privacy-preserving data release that aims to minimize the privacy leakage under utility constraints of a set of multiple tasks are investigated. While the private feature to be…

Data holders are increasingly seeking to protect their user's privacy, whilst still maximizing their ability to produce machine models with high quality predictions. In this work, we empirically evaluate various implementations of…

For many differentially private algorithms, such as the prominent noisy stochastic gradient descent (DP-SGD), the analysis needed to bound the privacy leakage of a single training run is well understood. However, few studies have reasoned…

Private computation, which includes techniques like multi-party computation and private query execution, holds great promise for enabling organizations to analyze data they and their partners hold while maintaining data subjects' privacy.…

We consider the problem of private distributed multi-party multiplication. It is well-established that Shamir secret-sharing coding strategies can enable perfect information-theoretic privacy in distributed computation via the celebrated…

In this paper, we address the problem of secure distributed computation in scenarios where user data is not uniformly distributed, extending existing frameworks that assume uniformity, an assumption that is challenging to enforce in data…

In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data. We consider a variant of this problem, where the input data can be shared for machine learning training…

In order to both learn and protect sensitive training data, there has been a growing interest in privacy preserving machine learning methods. Differential privacy has emerged as an important measure of privacy. We are interested in the…

Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples. Our work draws the connection between optimal robust learning and the privacy-utility tradeoff…

Privacy-preserving data release is about disclosing information about useful data while retaining the privacy of sensitive data. Assuming that the sensitive data is threatened by a brute-force adversary, we define Guessing Leakage as a…

Gaussian sketching, which consists of pre-multiplying the data with a random Gaussian matrix, is a widely used technique for multiple problems in data science and machine learning, with applications spanning computationally efficient…

A privacy-utility tradeoff is developed for an arbitrary set of finite-alphabet source distributions. Privacy is quantified using differential privacy (DP), and utility is quantified using expected Hamming distortion maximized over the set…

The rate-privacy function is defined in \cite{Asoodeh} as a tradeoff between privacy and utility in a distributed private data system in which both privacy and utility are measured using mutual information. Here, we use maximal correlation…

The rapid development of cloud computing has probably benefited each of us. However, the privacy risks brought by untrustworthy cloud servers arise the attention of more and more people and legislatures. In the last two decades, plenty of…

Privacy-protected microdata are often the desired output of a differentially private algorithm since microdata is familiar and convenient for downstream users. However, there is a statistical price for this kind of convenience. We show that…

A mechanism for releasing information about a statistical database with sensitive data must resolve a trade-off between utility and privacy. Privacy can be rigorously quantified using the framework of {\em differential privacy}, which…

This paper introduces quantum multiparty protocols which allow the use of temporary assumptions. We prove that secure quantum multiparty computations are possible if and only if classical multi party computations work. But these strict…

In this paper, we introduce a new notion of guaranteed privacy that requires that the change of the range of the corresponding inclusion function to the true function is small. In particular, leveraging mixed-monotone inclusion functions,…

We consider a fully-decentralized scenario in which no central trusted entity exists and all clients are honest-but-curious. The state-of-the-art approaches to this problem often rely on cryptographic protocols, such as multiparty…