Privacy Accounting

Follow this topic Ask about this topic

Latest papers

9 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Fast Privacy Loss Accounting for Random Allocation via Multiscale FFT
Oct 30, 2026Vitaly Feldman, Moshe ShenfeldPrivacy Accounting Differential Privacy
Can Rényi Accountants Beat Lossless Accountants for DP-SGD?
Oct 12, 2026Jinho BokPrivacy Accounting Rényi Differential Privacy
Department of Statistics and Data Science, University of Pennsylvania.
Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD
Oct 7, 2026Murat Bilgehan Ertan, Marten van DijkPrivacy Accounting Random Reshuffling
Affiliated with Vrije Universiteit Amsterdam.
Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD
Jun 3, 2026Xiaobo Huang, Fang XieDifferentially Private Stochastic Gradient Descent Privacy Accounting
Guangdong Provincial Key Laboratory of IRADS, Beijing · Normal-Hong Kong Baptist University · Zhuhai, China
Auditing Privacy in Multi-Tenant RAG under Account Collusion
May 19, 2026Florian A. D. BurnatAdversarial Attacks Privacy Auditing
University of Bath, Bath, UK.
Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
May 8, 2026Andy Dong, Ayfer ÖzgürDifferentially Private Stochastic Gradient Descent Privacy Accounting
Stanford University
When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
Mar 19, 2026Chen Yaoling, Liang Hao, Tu XiaotongPrivacy Accounting Differentially Private Federated Learning
School of Informatics, Xiamen University, China · Internet of Things Thrust, Hong Kong University of Science and Technology (Guangzhou), China
Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
Feb 26, 2026Meisam Mohammady, Qin Yang, Nicholas Stout +4Privacy Accounting Differentially Private Stochastic Gradient Descent
Iowa State University · University of Connecticut · University of Kansas
Efficient privacy loss accounting for subsampling and random allocation
Feb 19, 2026Vitaly Feldman, Moshe ShenfeldPrivacy Accounting Differential Privacy
Apple · The Hebrew University of Jerusalem · *Work partially done while author was an intern at Apple.

Oct 30, 2026J/K move · Enter open · S save

Fast Privacy Loss Accounting for Random Allocation via Multiscale FFT

Vitaly Feldman, Moshe Shenfeld

Privacy Accounting Differential Privacy

Open paper AskPDF arXiv

In the random allocation sampling scheme each user's data is used in

k

steps chosen randomly and uniformly from a sequence of

t

steps. This scheme is known to improve on Poisson sampling in private optimization and in communication-efficient aggregation. The existing privacy loss distribution (PLD) accountant for this scheme runs in time quadratic in the inverse of the accuracy parameter

α

(Feldman and Shenfeld, 2026). We give an algorithm, multiscale FFT, that represents likelihood ratios on a grid that is uniform within each dyadic interval and computes the exact rounding of every pairwise sum using FFTs within each interval. It keeps the guarantees of the accountant and improves the dependence of its running time on

α

from

O(α^{-2})

O(α^{-1}\log(1/α))

. In addition, we demonstrate that rounding can be performed via the mean-preserving connect-the-dots projection of (Doroshenko et al., 2026). This reduces the errors that rounding introduces in the mean of the privacy loss and in the

χ^2

divergence of the computed pair from the order of

α

O(α^2/\log(t))

. In our experiments, our algorithm achieves speedups of several orders of magnitude at high accuracy and gives improved privacy bounds for DP-SGD with PREAMBLE.