How to combine membership-inference attacks on multiple updated machine learning models
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 …
membership inference (MI) attacks that violate the privacy of the participants in the training …
[PDF][PDF] How to Combine Membership-Inference Attacks on Multiple Updated Machine Learning Models
M Jagielski, S Wu, A Oprea, J Ullman… - … on Privacy Enhancing …, 2023 - petsymposium.org
ABSTRACT 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 …
vulnerable to membership inference (MI) attacks that violate the privacy of the participants in …