Bayesian estimation of differential privacy
S Zanella-Beguelin, L Wutschitz… - International …, 2023 - proceedings.mlr.press
Abstract Algorithms such as Differentially Private SGD enable training machine learning
models with formal privacy guarantees. However, because these guarantees hold with …
models with formal privacy guarantees. However, because these guarantees hold with …
Group and attack: Auditing differential privacy
(ε, δ) differential privacy has seen increased adoption recently, especially in private machine
learning applications. While this privacy definition allows provably limiting the amount of …
learning applications. While this privacy definition allows provably limiting the amount of …
Unlocking accuracy and fairness in differentially private image classification
Privacy-preserving machine learning aims to train models on private data without leaking
sensitive information. Differential privacy (DP) is considered the gold standard framework for …
sensitive information. Differential privacy (DP) is considered the gold standard framework for …
Between privacy and utility: On differential privacy in theory and practice
J Seeman, D Susser - ACM Journal on Responsible Computing, 2024 - dl.acm.org
Differential privacy (DP) aims to confer data processing systems with inherent privacy
guarantees, offering strong protections for personal data. But DP's approach to privacy …
guarantees, offering strong protections for personal data. But DP's approach to privacy …
Evaluations of Machine Learning Privacy Defenses are Misleading
Empirical defenses for machine learning privacy forgo the provable guarantees of
differential privacy in the hope of achieving higher utility while resisting realistic adversaries …
differential privacy in the hope of achieving higher utility while resisting realistic adversaries …
On the risks of collecting multidimensional data under local differential privacy
The private collection of multiple statistics from a population is a fundamental statistical
problem. One possible approach to realize this is to rely on the local model of differential …
problem. One possible approach to realize this is to rely on the local model of differential …
[HTML][HTML] A standardised differential privacy framework for epidemiological modeling with mobile phone data
MK Savi, A Yadav, W Zhang, N Vembar… - PLOS Digital …, 2023 - journals.plos.org
During the COVID-19 pandemic, the use of mobile phone data for monitoring human
mobility patterns has become increasingly common, both to study the impact of travel …
mobility patterns has become increasingly common, both to study the impact of travel …
Advancing differential privacy: Where we are now and future directions for real-world deployment
In this article, we present a detailed review of current practices and state-of-the-art
methodologies in the field of differential privacy (DP), with a focus of advancing DP's …
methodologies in the field of differential privacy (DP), with a focus of advancing DP's …
Models matter: Setting accurate privacy expectations for local and central differential privacy
Differential privacy is a popular privacy-enhancing technology that has been deployed both
in industry and government agencies. Unfortunately, existing explanations of differential …
in industry and government agencies. Unfortunately, existing explanations of differential …
[PDF][PDF] Guidelines for evaluating differential privacy guarantees
This publication describes differential privacy—a mathematical framework that quantifies
privacy risk to individuals as a consequence of data collection and subsequent data release …
privacy risk to individuals as a consequence of data collection and subsequent data release …