The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
arXiv:2610. 09651v1 Announce Type: new Abstract: DP-SGD protects training data by adding Gaussian noise to clipped gradients.
arXiv:2605. 06259v3 Announce Type: replace Abstract: Within the $f$-DP framework, we derive a tight analysis of the trade-off function for Differentially Private Stochastic Gradient Descent (DP-SGD) with subsampling based on random allocation in which each sample is independently assigned to exactly one of $M$ minibatches per epoch, each minibatch corresponding to one of the $M$ SGD rounds within a single epoch.
arXiv:2601. 10237v3 Announce Type: replace Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is the dominant paradigm for private training, but its fundamental limitations under worst-case adversarial privacy definitions remain poorly understood.
The paper investigates the sample complexity required for membership‑inference attacks, focusing on Gaussian mean estimation. It shows that, in this setting, an attacker may need at least Ω(n + n^2 ho^2) reference samples to match a fully informed adversary, which can be far more than the n samples used by the learning algorithm. This demonstrates that practical attacks, which typically use only O(n) samples, might underestimate the true risk of membership inference.
The paper introduces Pairwise Likelihood MIA (PL‑MIA), a unified membership inference attack that combines a Gaussian likelihood‑ratio statistic with population calibration and the Cauchy combination test. PL‑MIA generates p‑values from pairwise comparisons between a query point and reference points, then aggregates these continuous signals using the Cauchy test to preserve evidence strength. Experiments show that PL‑MIA surpasses strong baselines, boosting true positive rates by over 25% in low‑false‑positive settings, thereby validating the theoretical advantages of the proposed statistical framework.
arXiv:2509. 25003v3 Announce Type: replace Abstract: Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set.