Open Access
ARTICLE
A Performance Study of Membership Inference Attacks on Different Machine Learning Algorithms
Jumana Alsubhi1, Abdulrahman Gharawi1, Mohammad Alahmadi2,*
1
Department of Computer Science, University of Georgia, Athens, GA, 30602, USA
2
Department of Software Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah, 23890,
Saudi Arabia
* Corresponding Author: Mohammad Alahmadi. Email:
Journal of Information Hiding and Privacy Protection 2021, 3(4), 193-200. https://doi.org/10.32604/jihpp.2021.027871
Received 26 January 2022; Accepted 03 March 2022; Issue published 22 March 2022
Abstract
Nowadays, machine learning (ML) algorithms cannot succeed without
the availability of an enormous amount of training data. The data could contain
sensitive information, which needs to be protected. Membership inference
attacks attempt to find out whether a target data point is used to train a certain
ML model, which results in security and privacy implications. The leakage of
membership information can vary from one machine-learning algorithm to
another. In this paper, we conduct an empirical study to explore the performance
of membership inference attacks against three different machine learning
algorithms, namely, K-nearest neighbors, random forest, support vector machine,
and logistic regression using three datasets. Our experiments revealed the best
machine learning model that can be more immune to privacy attacks.
Additionally, we examined the effects of such attacks when varying the dataset
size. Based on our observations for the experimental results, we propose a
defense mechanism that is less prone to privacy attacks and demonstrate its
effectiveness through an empirical evaluation.
Keywords
Cite This Article
J. Alsubhi, A. Gharawi and M. Alahmadi, "A performance study of membership inference attacks on different machine learning algorithms,"
Journal of Information Hiding and Privacy Protection, vol. 3, no.4, pp. 193–200, 2021. https://doi.org/10.32604/jihpp.2021.027871