Technical privacy metrics: a systematic survey
The goal of privacy metrics is to measure the degree of privacy enjoyed by users in a system
and the amount of protection offered by privacy-enhancing technologies. In this way, privacy …
and the amount of protection offered by privacy-enhancing technologies. In this way, privacy …
When federated learning meets privacy-preserving computation
J Chen, H Yan, Z Liu, M Zhang, H Xiong… - ACM Computing Surveys, 2024 - dl.acm.org
Nowadays, with the development of artificial intelligence (AI), privacy issues attract wide
attention from society and individuals. It is desirable to make the data available but invisible …
attention from society and individuals. It is desirable to make the data available but invisible …
Advances and open problems in federated learning
Federated learning (FL) is a machine learning setting where many clients (eg, mobile
devices or whole organizations) collaboratively train a model under the orchestration of a …
devices or whole organizations) collaboratively train a model under the orchestration of a …
Practical secure aggregation for privacy-preserving machine learning
We design a novel, communication-efficient, failure-robust protocol for secure aggregation of
high-dimensional data. Our protocol allows a server to compute the sum of large, user-held …
high-dimensional data. Our protocol allows a server to compute the sum of large, user-held …
Rényi differential privacy
I Mironov - 2017 IEEE 30th computer security foundations …, 2017 - ieeexplore.ieee.org
We propose a natural relaxation of differential privacy based on the Rényi divergence.
Closely related notions have appeared in several recent papers that analyzed composition …
Closely related notions have appeared in several recent papers that analyzed composition …
Privacy preserving vertical federated learning for tree-based models
Federated learning (FL) is an emerging paradigm that enables multiple organizations to
jointly train a model without revealing their private data to each other. This paper studies {\it …
jointly train a model without revealing their private data to each other. This paper studies {\it …
The algorithmic foundations of differential privacy
The problem of privacy-preserving data analysis has a long history spanning multiple
disciplines. As electronic data about individuals becomes increasingly detailed, and as …
disciplines. As electronic data about individuals becomes increasingly detailed, and as …
Federated learning with bayesian differential privacy
A Triastcyn, B Faltings - … Conference on Big Data (Big Data), 2019 - ieeexplore.ieee.org
We consider the problem of reinforcing federated learning with formal privacy guarantees.
We propose to employ Bayesian differential privacy, a relaxation of differential privacy for …
We propose to employ Bayesian differential privacy, a relaxation of differential privacy for …
The complexity of differential privacy
S Vadhan - Tutorials on the Foundations of Cryptography …, 2017 - Springer
Differential privacy is a theoretical framework for ensuring the privacy of individual-level data
when performing statistical analysis of privacy-sensitive datasets. This tutorial provides an …
when performing statistical analysis of privacy-sensitive datasets. This tutorial provides an …
Boosting and differential privacy
C Dwork, GN Rothblum… - 2010 IEEE 51st annual …, 2010 - ieeexplore.ieee.org
Boosting is a general method for improving the accuracy of learning algorithms. We use
boosting to construct improved privacy-pre serving synopses of an input database. These …
boosting to construct improved privacy-pre serving synopses of an input database. These …