29 citations · 46 across the 12 of their papers we have counts for
17 papers
Contraction and Statistical Inference under Privacy for Uniformly Bounded Distributions
Leonhard Grosse, Sara Saeidian, Tobias J. Oechtering +1
We investigate -interior pointwise maximal leakage (PML) as a tool for contraction analyses and disclosure control. Based on the strong adversarial threat models from maximal le…
Information Leakage Envelopes
Sara Saeidian, Carlos Pinzón, Catuscia Palamidessi
We study privacy guarantees in the framework of pointwise maximal leakage (PML) that satisfy two requirements: they are robust under post-processing and upper bound the failure pro…
On the Information Leakage Envelope of the Gaussian Mechanism
Sara Saeidian
We study the pointwise maximal leakage (PML) envelope of the Gaussian mechanism, which characterizes the smallest information leakage bound that holds with high probability under a…
Dobrushin Coefficients of Private Mechanisms Beyond Local Differential Privacy
Leonhard Grosse, Sara Saeidian, Tobias J. Oechtering +1
We investigate Dobrushin coefficients of discrete Markov kernels that have bounded pointwise maximal leakage (PML) with respect to all distributions with a minimum probability mass…
Context-aware Privacy Bounds for Linear Queries
Heng Zhao, Sara Saeidian, Tobias J. Oechtering
Linear queries, as the basis of broad analysis tasks, are often released through privacy mechanisms based on differential privacy (DP), the most popular framework for privacy prote…
Privacy Mechanism Design based on Empirical Distributions
Leonhard Grosse, Sara Saeidian, Mikael Skoglund +1
Pointwise maximal leakage (PML) is a per-outcome privacy measure based on threat models from quantitative information flow. Privacy guarantees with PML rely on knowledge about the…
A Tight Context-aware Privacy Bound for Histogram Publication
Sara Saeidian, Ata Yavuzyılmaz, Leonhard Grosse +2
We analyze the privacy guarantees of the Laplace mechanism releasing the histogram of a dataset through the lens of pointwise maximal leakage (PML). While differential privacy is c…
Evaluating Differential Privacy on Correlated Datasets Using Pointwise Maximal Leakage
Sara Saeidian, Tobias J. Oechtering, Mikael Skoglund
Data-driven advancements significantly contribute to societal progress, yet they also pose substantial risks to privacy. In this landscape, differential privacy (DP) has become a c…
Bounds on the privacy amplification of arbitrary channels via the contraction of -divergence
Leonhard Grosse, Sara Saeidian, Tobias J. Oechtering +1
We examine the privacy amplification of channels that do not necessarily satisfy any LDP guarantee by analyzing their contraction behavior in terms of -divergence, an -dive…
Information Density Bounds for Privacy
Sara Saeidian, Leonhard Grosse, Parastoo Sadeghi +2
This paper explores the implications of guaranteeing privacy by imposing a lower bound on the information density between the private and the public data. We introduce a novel and…
Quantifying Privacy via Information Density
Leonhard Grosse, Sara Saeidian, Parastoo Sadeghi +2
We examine the relationship between privacy metrics that utilize information density to measure information leakage between a private and a disclosed random variable. Firstly, we p…
Extremal Mechanisms for Pointwise Maximal Leakage
Leonhard Grosse, Sara Saeidian, Tobias Oechtering
Data publishing under privacy constraints can be achieved with mechanisms that add randomness to data points when released to an untrusted party, thereby decreasing the data's util…
Pointwise Maximal Leakage on General Alphabets
Sara Saeidian, Giulia Cervia, Tobias J. Oechtering +1
Pointwise maximal leakage (PML) is an operationally meaningful privacy measure that quantifies the amount of information leaking about a secret to a single outcome of a related…
Rethinking Disclosure Prevention with Pointwise Maximal Leakage
Sara Saeidian, Giulia Cervia, Tobias J. Oechtering +1
This paper introduces a paradigm shift in the way privacy is defined, driven by a novel interpretation of the fundamental result of Dwork and Naor about the impossibility of absolu…
Pointwise Maximal Leakage
Sara Saeidian, Giulia Cervia, Tobias J. Oechtering +1
We introduce a privacy measure called pointwise maximal leakage, generalizing the pre-existing notion of maximal leakage, which quantifies the amount of information leaking about a…
Optimal Maximal Leakage-Distortion Tradeoff
Sara Saeidian, Giulia Cervia, Tobias J. Oechtering +1
Most methods for publishing data with privacy guarantees introduce randomness into datasets which reduces the utility of the published data. In this paper, we study the privacy-uti…
Quantifying Membership Privacy via Information Leakage
Sara Saeidian, Giulia Cervia, Tobias J. Oechtering +1
Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of a…