Membership Inference Attack Using Self Influence Functions. (arXiv:2205.13680v1 [cs.LG])

Member inference (MI) attacks aim to determine if a specific data sample was
used to train a machine learning model. Thus, MI is a major privacy threat to
models trained on private sensitive data, such as medical records. In MI
attacks one may consider the black-box settings, where the model's parameters
and activations are hidden from the adversary, or the white-box case where they
are available to the attacker. In this work, we focus on the latter and present
a …

arxiv inference influence