The paper introduces Private Best-of-N (PrivBoN), a method that adds calibrated Gumbel noise to reward scores during inference-time alignment, achieving both ε-differential privacy and KL-regularized alignment. When the privacy budget exceeds a critical threshold ε*, the noise becomes regret-optimal, matching the theoretical alignment skyline. The authors also propose Private Inference-Time Pessimism (PrivITP), which uses χ^2-regularized rejection sampling and a two-phase Gaussian mechanism to provide ex-post (ε,δ)-DP with a privacy cost independent of the number of responses, and demonstrate that both methods outperform standard Best-of-N across multiple models and datasets.
By Ishi Jain, Nandini Bhattad, Sayak Ray Chowdhury
arXiv:2310. 10092v4 Announce Type: replace Abstract: This paper explores the use of linear aggregation to protect the privacy of sensitive training labels through the concept of \emph{label differential privacy} (label-DP) while maintaining regression task utility.
By Anand Brahmbhatt, Rishi Saket, Shreyas Havaldar, Anshul Nasery, Yukti Makhija, Aravindan Raghuveer
arXiv:2606. 01527v2 Announce Type: replace Abstract: Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten.
By Matthew Regehr, Gautam Kamath, Andrew Lowy
arXiv:2610.07212v1 Announce Type: new
Abstract: Reinforcement learning with verifiable rewards (RLVR) trains a language model on problems that may themselves be confidential, and the trained model ca...
By Jiachen Zhao, Antonia Januszewicz, Taeho Jung
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.
By Murat Bilgehan Ertan, Marten van Dijk
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.
By Marten van Dijk, Murat Bilgehan Ertan
The paper addresses the challenge of selecting external datasets for private transfer learning by modeling high‑dimensional regression with heterogeneous sources and a weighted ridge estimator. It relies solely on aggregated statistics and offers privacy guarantees under $
ho$‑zero‑concentrated differential privacy for labels or both features and labels. A deterministic equivalent of test error is derived, enabling optimization of hyperparameters and decision‑making about the utility of private external data without accessing individual records.
By Filip Kova\v{c}evi\'c, Edwige Cyffers, Stefano Sarao Mannelli, Marco Mondelli
arXiv:2512. 04008v2 Announce Type: replace Abstract: Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model.
By Zo\"e Ruha Bell, Anvith Thudi, Olive Franzese-McLaughlin, Nicolas Papernot, Shafi Goldwasser
arXiv:2605. 19813v2 Announce Type: replace Abstract: Federated differentially private protocols can communicate over many adaptive rounds and reuse each client's local samples.
By T. Tony Cai, Yicheng Li
arXiv:2602. 01607v3 Announce Type: replace-cross Abstract: Differentially private synthetic data enables the sharing and analysis of sensitive datasets while providing rigorous privacy guarantees for individual contributors.
By Rundong Ding, Yiyun He, Yizhe Zhu
arXiv:2607. 29675v1 Announce Type: cross Abstract: Density modes provide a localized and interpretable summary of multimodal distributions, but their estimation under rigorous differential privacy constraints remains largely unexplored.
By Arkajyoti Bhattacharjee, Arnab Auddy
arXiv:2610. 02716v1 Announce Type: new Abstract: Objective perturbation adds a random linear term to a regularized empirical risk and releases the exact perturbed minimizer.
By Austin Watkins, Raman Arora