How Much Does Each Datapoint Leak Your Privacy? Quantifying the Per-datum Membership Leakage

arXiv:2402.10065v1 Announce Type: new
Abstract: We study the per-datum Membership Inference Attacks (MIAs), where an attacker aims to infer whether a fixed target datum has been included in the input dataset of an algorithm and thus, violates privacy. First, we define the membership leakage of a datum as the advantage of the optimal adversary targeting to identify it. Then, we quantify the per-datum membership leakage for the empirical mean, and show that it depends on the Mahalanobis distance between the …

abstract algorithm arxiv attacks cs.cr cs.lg dataset inference leak math.st per privacy stat.ml stat.th study type