Machine learning models can leak private information about their training data, but the standard methods to measure this risk, based on membership inference attacks (MIAs), have …
Membership inference is one of the simplest privacy threats faced by machine learning models that are trained on private sensitive data. In this attack, an adversary infers whether a …
Membership inference attacks are a key measure to evaluate privacy leakage in machine learning (ML) models. It is important to train ML models that have high membership privacy …
Data used to train machine learning (ML) models can be sensitive. Membership inference attacks (MIAs), attempting to determine whether a particular data record was used to train an …
S Chen, W Wang, Y Zhong, Z Ying, W Tang, Z Pan - Computers & Security, 2024 - Elsevier
Abstract Membership Inference Attacks (MIAs) have been considered as one of the major privacy threats in recent years, especially in machine learning models. Most canonical MIAs …
A large body of research has shown that machine learning models are vulnerable to membership inference (MI) attacks that violate the privacy of the participants in the training …
S Rahimian, T Orekondy, M Fritz - arXiv preprint arXiv:2009.00395, 2020 - arxiv.org
Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which …
L Song, P Mittal - 30th USENIX Security Symposium (USENIX Security …, 2021 - usenix.org
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was …
It is observed in the literature that data augmentation can significantly mitigate membership inference (MI) attack. However, in this work, we challenge this observation by proposing new …