How to dp-fy ml: A practical guide to machine learning with differential privacy

N Ponomareva, H Hazimeh, A Kurakin, Z Xu… - Journal of Artificial …, 2023 - jair.org
Abstract Machine Learning (ML) models are ubiquitous in real-world applications and are a
constant focus of research. Modern ML models have become more complex, deeper, and …

Differential privacy techniques for cyber physical systems: A survey

MU Hassan, MH Rehmani… - … Communications Surveys & …, 2019 - ieeexplore.ieee.org
Modern cyber physical systems (CPSs) has widely being used in our daily lives because of
development of information and communication technologies (ICT). With the provision of …

The algorithmic foundations of differential privacy

C Dwork, A Roth - Foundations and Trends® in Theoretical …, 2014 - nowpublishers.com
The problem of privacy-preserving data analysis has a long history spanning multiple
disciplines. As electronic data about individuals becomes increasingly detailed, and as …

Semi-supervised knowledge transfer for deep learning from private training data

N Papernot, M Abadi, U Erlingsson… - ar**_Problem_MLF/links/0deec5328063473edc000000/A-Practical-Parameterized-Algorithm-for-the-Individual-Haploty**-Problem-MLF.pdf#page=12" data-clk="hl=en&sa=T&oi=gga&ct=gga&cd=4&d=1556140885074473433&ei=CS2vZ6DWFuzDieoP2tyjoAc" data-clk-atid="2XFT4-OFmBUJ" target="_blank">[PDF] researchgate.net

Differential privacy: A survey of results

C Dwork - International conference on theory and applications of …, 2008 - Springer
Over the past five years a new approach to privacy-preserving data analysis has born fruit
[13, 18, 7, 19, 5, 37, 35, 8, 32]. This approach differs from much (but not all!) of the related …

Evaluating differentially private machine learning in practice

B Jayaraman, D Evans - 28th USENIX Security Symposium (USENIX …, 2019 - usenix.org
Differential privacy is a strong notion for privacy that can be used to prove formal
guarantees, in terms of a privacy budget, ε, about how much information is leaked by a …

Mechanism design via differential privacy

F McSherry, K Talwar - 48th Annual IEEE Symposium on …, 2007 - ieeexplore.ieee.org
We study the role that privacy-preserving algorithms, which prevent the leakage of specific
information about participants, can play in the design of mechanisms for strategic agents …

Differentially private learning needs better features (or much more data)

F Tramer, D Boneh - arxiv preprint arxiv:2011.11660, 2020 - arxiv.org
We demonstrate that differentially private machine learning has not yet reached its" AlexNet
moment" on many canonical vision tasks: linear models trained on handcrafted features …

[PDF][PDF] Differentially private empirical risk minimization.

K Chaudhuri, C Monteleoni, AD Sarwate - Journal of Machine Learning …, 2011 - jmlr.org
Privacy-preserving machine learning algorithms are crucial for the increasingly common
setting in which personal data, such as medical or financial records, are analyzed. We …

Anonymization techniques for privacy preserving data publishing: A comprehensive survey

A Majeed, S Lee - IEEE access, 2020 - ieeexplore.ieee.org
Anonymization is a practical solution for preserving user's privacy in data publishing. Data
owners such as hospitals, banks, social network (SN) service providers, and insurance …