Supervised Machine Learning with Plausible Deniability

06/08/2021
by   Stefan Rass, et al.
0

We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data, or equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While this is easy to answer negatively in the most general case, it is interesting to note that the protection extends over non-recoverability towards plausible deniability: Given an ML model f, we show that one can take a set of purely random training data, and from this define a suitable “learning rule” that will produce a ML model that is exactly f. Thus, any speculation about which data has been used to train f is deniable upon the claim that any other data could have led to the same results. We corroborate our theoretical finding with practical examples, and open source implementations of how to find the learning rules for a chosen set of raining data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/10/2020

Managing Data Lineage of O G Machine Learning Models: The Sweet Spot for Shale Use Case

Machine Learning (ML) has increased its role, becoming essential in seve...
research
03/15/2018

Chiron: Privacy-preserving Machine Learning as a Service

Major cloud operators offer machine learning (ML) as a service, enabling...
research
09/28/2018

Reuse and Adaptation for Entity Resolution through Transfer Learning

Entity resolution (ER) is one of the fundamental problems in data integr...
research
09/04/2022

Data Provenance via Differential Auditing

Auditing Data Provenance (ADP), i.e., auditing if a certain piece of dat...
research
06/19/2013

Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers

Machine Learning (ML) algorithms are used to train computers to perform ...
research
04/15/2021

Facilitating Machine Learning Model Comparison and Explanation Through A Radial Visualisation

Building an effective Machine Learning (ML) model for a data set is a di...

Please sign up or login with your details

Forgot password? Click here to reset