Reliable Estimation of Differential Privacy under Selection Bias↗ (원문, 새 창)

본문 미리보기

arXiv:2610.27021v1 Announce Type: new Abstract: Statistical privacy audits are essential for verifying the theoretical privacy guarantees of differentially private (DP) mechanisms. Auditors typically use Membership Inference Attacks (MIAs) to estimate a lower bound on the true privacy leakage of DP mechanisms at a specified confidence level, which should not exceed the theoretical privacy upper bound guaranteed by DP. However, we found that many auditing implementations in prior work introduce