Senavirathne, Navoda and Torra, Vicenç
(2019)
Integrally private model selection for decision trees.
Computers and Security, 83.
pp. 167-181.
ISSN 0167-4048
Abstract
Privacy attacks targeting machine learning models are evolving. One of the primary goals of
such attacks is to infer information about the training data used to construct the models.
“Integral Privacy”focuses on machine learning and statistical models which explain how we
can utilize intruder’s uncertainty to provide a privacy guarantee against model comparison
attacks.
Through experimental results, we show how the distribution of models can be used to
achieve integral privacy. Here, we observe two categories of machine learning models based
on their frequency of occurrence in the model space. Then we explain the privacy implications
of selecting each of them based on a new attack model and empirical results. Also,
we provide recommendations for private model selection based on the accuracy and stabil-
ity of the models along with the diversity of training data that can be used to generate the
models.
| Item Type: |
Article
|
| Keywords: |
Integral privacy;
Privacy models;
Data privacy;
Machine learning model space;
Privacy preserving machine learning; |
| Academic Unit: |
Faculty of Science and Engineering > Research Institutes > Hamilton Institute |
| Item ID: |
14063 |
| Identification Number: |
https://doi.org/10.1016/j.cose.2019.01.006 |
| Depositing User: |
Vicenç Torra
|
| Date Deposited: |
24 Feb 2021 14:50 |
| Journal or Publication Title: |
Computers and Security |
| Publisher: |
Elsevier |
| Refereed: |
Yes |
| URI: |
|
| Use Licence: |
This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available
here |
Repository Staff Only(login required)
 |
Item control page |
Downloads per month over past year
Origin of downloads
Altmetric
Altmetric