Saved in:
Bibliographic Details
Main Authors: Liu, Yifeng, Wang, Zehua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.17012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909673050865664
author Liu, Yifeng
Wang, Zehua
author_facet Liu, Yifeng
Wang, Zehua
contents As data-driven technologies advance swiftly, maintaining strong privacy measures becomes progressively difficult. Conventional $(ε, δ)$-differential privacy, while prevalent, exhibits limited adaptability for many applications. To mitigate these constraints, we present alpha differential privacy (ADP), an innovative privacy framework grounded in alpha divergence, which provides a more flexible assessment of privacy consumption. This study delineates the theoretical underpinnings of ADP and contrasts its performance with competing privacy frameworks across many scenarios. Empirical assessments demonstrate that ADP offers enhanced privacy guarantees in small to moderate iteration contexts, particularly where severe privacy requirements are necessary. The suggested method markedly improves privacy-preserving methods, providing a flexible solution for contemporary data analysis issues in a data-centric environment.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17012
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Novel Approach to Differential Privacy with Alpha Divergence
Liu, Yifeng
Wang, Zehua
Cryptography and Security
As data-driven technologies advance swiftly, maintaining strong privacy measures becomes progressively difficult. Conventional $(ε, δ)$-differential privacy, while prevalent, exhibits limited adaptability for many applications. To mitigate these constraints, we present alpha differential privacy (ADP), an innovative privacy framework grounded in alpha divergence, which provides a more flexible assessment of privacy consumption. This study delineates the theoretical underpinnings of ADP and contrasts its performance with competing privacy frameworks across many scenarios. Empirical assessments demonstrate that ADP offers enhanced privacy guarantees in small to moderate iteration contexts, particularly where severe privacy requirements are necessary. The suggested method markedly improves privacy-preserving methods, providing a flexible solution for contemporary data analysis issues in a data-centric environment.
title A Novel Approach to Differential Privacy with Alpha Divergence
topic Cryptography and Security
url https://arxiv.org/abs/2506.17012