Let's Ask Gauss: Improved One-Run Privacy Auditing
The paper introduces a one-run white-box privacy auditor for Differentially Private Stochastic Gradient Descent (DP-SGD). It exploits the asymptotic Gaussian distribution of canary-aligned observations to derive tighter privacy lower bounds than previous methods. This new framework uses sequential observations and Gaussian modeling to provide a more accurate estimate of the privacy parameter epsilon in a single training run.