Related papers: PAC Privacy: Automatic Privacy Measurement and Con…
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…
Linear regression is a fundamental tool for statistical analysis, which has motivated the development of linear regression methods that satisfy provable privacy guarantees so that the learned model reveals little about any one data point…
A deterministic privacy metric using non-stochastic information theory is developed. Particularly, minimax information is used to construct a measure of information leakage, which is inversely proportional to the measure of privacy. Anyone…
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 probability, i.e., the probability that the information leakage…
A commonly used method to protect user privacy in data collection is to perform randomized perturbation on user's real data before collection so that aggregated statistics can still be inferred without endangering secrets held by…
Online services such as web search and e-commerce applications typically rely on the collection of data about users, including details of their activities on the web. Such personal data is used to enhance the quality of service via…
Privacy and security are central to the design of information systems endowed with sound data protection and cyber resilience capabilities. Still, developers often struggle to incorporate these properties into software projects as they…
Many modern statistical analysis and machine learning applications require training models on sensitive user data. Under a formal definition of privacy protection, differentially private algorithms inject calibrated noise into the…
This work proposes an algorithmic method to verify differential privacy for estimation mechanisms with performance guarantees. Differential privacy makes it hard to distinguish outputs of a mechanism produced by adjacent inputs. While…
Differential privacy mechanisms such as the Gaussian or Laplace mechanism have been widely used in data analytics for preserving individual privacy. However, they are mostly designed for continuous outputs and are unsuitable for scenarios…
Recently, there has been a number of papers relating mechanism design and privacy (e.g., see \cite{MT07,Xia11,CCKMV11,NST12,NOS12,HK12}). All of these papers consider a worst-case setting where there is no probabilistic information about…
We consider the problem of computing tight privacy guarantees for the composition of subsampled differentially private mechanisms. Recent algorithms can numerically compute the privacy parameters to arbitrary precision but must be carefully…
Amplification by subsampling is one of the main primitives in machine learning with differential privacy (DP): Training a model on random batches instead of complete datasets results in stronger privacy. This is traditionally formalized via…
The Maximal Information Coefficient (MIC) is a powerful statistic to identify dependencies between variables. However, it may be applied to sensitive data, and publishing it could leak private information. As a solution, we present…
We propose a discrete privacy mechanism exploiting beneficial properties of the novel privacy measure Pointwise Maximal Leakage (PML). Given the utility assignment characterized by every input-output letter pair, we study the mechanism…
Differential privacy (DP) is a mathematical definition of privacy that can be widely applied when publishing data. DP has been recognized as a potential means of adhering to various privacy-related legal requirements. However, it can be…
We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant…
Synthetic data generation is gaining traction as a privacy enhancing technology (PET). When properly generated, synthetic data preserve the analytic utility of real data while avoiding the retention of information that would allow the…
We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard…
The notion of replicable algorithms was introduced in Impagliazzo et al. [STOC '22] to describe randomized algorithms that are stable under the resampling of their inputs. More precisely, a replicable algorithm gives the same output with…