We have 3 of 10 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
In this article, we study deep nonparametric regression trained via stochastic gradient Langevin dynamics (SGLD), a variant of stochastic gradient descent that injects carefully calibrated Gaussian noise during optimization. Using a PAC-Bayesian analysis tailored to deep ReLU networks, we establish an excess-risk bound...
Pairwise Likelihood MIA (PL-MIA), a unified method that combines a Gaussian likelihood-ratio (GLR) statistic with population calibration and the Cauchy combination test, is proposed, demonstrating how statistical principles can turn noisy model outputs into more powerful, calibrated, and reproducible evidence for membe...
Word-level Probability MIA (WPMIA) is proposed, a statistically principled MIA for strict black-box privacy auditing that estimates word-level generation probabilities via Monte Carlo sampling with local kernel smoothing, then aggregates these estimates into a sequence-level likelihood estimator.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
