Related papers: $(\ell,\delta)$-Diversity: Linkage-Robustness via …
We formally study two methods for data sanitation that have been used extensively in the database community: k-anonymity and l-diversity. We settle several open problems concerning the difficulty of applying these methods optimally, proving…
Data providers such as government statistical agencies perform a balancing act: maximising information published to inform decision-making and research, while simultaneously protecting privacy. The emergence of identified administrative…
We study the fundamental problems of identity testing (goodness of fit), and closeness testing (two sample test) of distributions over $k$ elements, under differential privacy. While the problems have a long history in statistics, finite…
We introduce a family of information leakage measures called maximal $(\alpha,\beta)$-leakage (M$\alpha$beL), parameterized by real numbers $\alpha$ and $\beta$ greater than or equal to 1. The measure is formalized via an operational…
Maximum diversity aims at selecting a diverse set of high-quality objects from a collection, which is a fundamental problem and has a wide range of applications, e.g., in Web search. Diversity under a uniform or partition matroid constraint…
Decentralized learning (DL) offers a novel paradigm in machine learning by distributing training across clients without central aggregation, enhancing scalability and efficiency. However, DL's peer-to-peer model raises challenges in…
This work investigates the effectiveness of different pseudonymization techniques, ranging from rule-based substitutions to using pre-trained Large Language Models (LLMs), on a variety of datasets and models used for two widely used NLP…
The powerful cooperation of federated learning (FL) and differential privacy~(DP) provides a promising paradigm for the large-scale private clients. However, existing analyses in FL-DP mostly rely on the composition theorem and cannot…
To resolve the acute problem of privacy protection and guarantee that data can be used in the context of threat intelligence, this paper considers the implementation of Differential Privacy (DP) in cybersecurity analytics. DP, which is a…
Privacy risks in differentially private (DP) systems increase significantly when data is correlated, as standard DP metrics often underestimate the resulting privacy leakage, leaving sensitive information vulnerable. Given the ubiquity of…
We propose a novel problem formulation to address the privacy-utility tradeoff, specifically when dealing with two distinct user groups characterized by unique sets of private and utility attributes. Unlike previous studies that primarily…
This chapter is meant to be part of the book "Differential Privacy for Artificial Intelligence Applications." We give an introduction to the most important property of differential privacy -- composition: running multiple independent…
This paper proposes an $\alpha$-lift measure for data privacy and determines the optimal privatization scheme that minimizes the $\alpha$-lift in the watchdog method. To release data $X$ that is correlated with sensitive information $S$,…
Distributed data analysis without revealing the individual data has recently attracted significant attention in several applications. A collaborative data analysis through sharing dimensionality reduced representations of data has been…
Location entropy (LE) is a popular metric for measuring the popularity of various locations (e.g., points-of-interest). Unlike other metrics computed from only the number of (unique) visits to a location, namely frequency, LE also captures…
While the introduction of differential privacy has been a major breakthrough in the study of privacy preserving data publication, some recent work has pointed out a number of cases where it is not possible to limit inference about…
In recent years, Local Differential Privacy (LDP), a robust privacy-preserving methodology, has gained widespread adoption in real-world applications. With LDP, users can perturb their data on their devices before sending it out for…
Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments investigating the effects of using different approaches to…
Dataset distillation (DD) compresses large datasets into smaller ones while preserving the performance of models trained on them. Although DD is often assumed to enhance data privacy by aggregating over individual examples, recent studies…
This work examines a novel question: how much randomness is needed to achieve local differential privacy (LDP)? A motivating scenario is providing {\em multiple levels of privacy} to multiple analysts, either for distribution or for…