Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification

11/29/2021
by   Dominique Mercier, et al.
10

With the advent of machine learning in applications of critical infrastructure such as healthcare and energy, privacy is a growing concern in the minds of stakeholders. It is pivotal to ensure that neither the model nor the data can be used to extract sensitive information used by attackers against individuals or to harm whole societies through the exploitation of critical infrastructure. The applicability of machine learning in these domains is mostly limited due to a lack of trust regarding the transparency and the privacy constraints. Various safety-critical use cases (mostly relying on time-series data) are currently underrepresented in privacy-related considerations. By evaluating several privacy-preserving methods regarding their applicability on time-series data, we validated the inefficacy of encryption for deep learning, the strong dataset dependence of differential privacy, and the broad applicability of federated methods.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

page 6

page 9

07/10/2017

Composition Properties of Inferential Privacy for Time-Series Data

With the proliferation of mobile devices and the internet of things, dev...
06/03/2020

A Distributed Trust Framework for Privacy-Preserving Machine Learning

When training a machine learning model, it is standard procedure for the...
10/25/2019

Substra: a framework for privacy-preserving, traceable and collaborative Machine Learning

Machine learning is promising, but it often needs to process vast amount...
03/29/2021

Privacy and Trust Redefined in Federated Machine Learning

A common privacy issue in traditional machine learning is that data need...
05/23/2019

Privacy-Preserving Obfuscation of Critical Infrastructure Networks

The paper studies how to release data about a critical infrastructure ne...
10/26/2021

Data-Driven Time Series Reconstruction for Modern Power Systems Research

A critical aspect of power systems research is the availability of suita...
02/09/2020

Privacy-Preserving Image Classification in the Local Setting

Image data has been greatly produced by individuals and commercial vendo...

Code Repositories

PPML-TSA

Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.