Related papers: Privacy against a Hypothesis Testing Adversary

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Private closeness testing asks to decide whether the underlying probability distributions of two sensitive datasets are identical or differ significantly in statistical distance, while guaranteeing (differential) privacy of the data. As in…

Local Differential Privacy (LDP) protocols allow an aggregator to obtain population statistics about sensitive data of a userbase, while protecting the privacy of the individual users. To understand the tradeoff between aggregator utility…

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…

In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development. Differential privacy (DP) has emerged as one canonical…

We address the problem of defending predictive models, such as machine learning classifiers (Defender models), against membership inference attacks, in both the black-box and white-box setting, when the trainer and the trained model are…

Theoretical and applied research into privacy encompasses an incredibly broad swathe of differing approaches, emphasis and aims. This work introduces a new quantitative notion of privacy that is both contextual and specific. We argue that…

We introduce Epsilon*, a new privacy metric for measuring the privacy risk of a single model instance prior to, during, or after deployment of privacy mitigation strategies. The metric requires only black-box access to model predictions,…

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…

To analyze the privacy guarantee of personal data in a database that is subject to queries it is necessary to model the prior knowledge of a possible attacker. Differential privacy considers a worst-case scenario where he knows almost…

We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive…

We study simple binary hypothesis testing under both local differential privacy (LDP) and communication constraints. We qualify our results as either minimax optimal or instance optimal: the former hold for the set of distribution pairs…

A face image not only provides details about the identity of a subject but also reveals several attributes such as gender, race, sexual orientation, and age. Advancements in machine learning algorithms and popularity of sharing images on…

Adversarial robustness, the ability of a model to withstand manipulated inputs that cause errors, is essential for ensuring the trustworthiness of machine learning models in real-world applications. However, previous studies have shown that…

In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…

The problem of private information "leakage" (inadvertently or by malicious design) from the myriad large centralized searchable data repositories drives the need for an analytical framework that quantifies unequivocally how safe private…

The design of a statistical signal processing privacy problem is studied where the private data is assumed to be observable. In this work, an agent observes useful data $Y$, which is correlated with private data $X$, and wants to disclose…

Differential privacy is a de facto standard in data privacy, with applications in the public and private sectors. A way to explain differential privacy, which is particularly appealing to statistician and social scientists is by means of…

Numerous generalization techniques have been proposed for privacy preserving data publishing. Most existing techniques, however, implicitly assume that the adversary knows little about the anonymization algorithm adopted by the data…

Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients'…