Privacy-Preserving Learning-Augmented Data Structures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Goyal, Prabhav, Sridhar, Vinesh, Zheng, Wilson
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908571006926848
author Goyal, Prabhav
Sridhar, Vinesh
Zheng, Wilson
author_facet Goyal, Prabhav
Sridhar, Vinesh
Zheng, Wilson
contents Learning-augmented data structures use predicted frequency estimates to retrieve frequently occurring database elements faster than standard data structures. Recent work has developed data structures that optimally exploit these frequency estimates while maintaining robustness to adversarial prediction errors. However, the privacy and security implications of this setting remain largely unexplored. In the event of a security breach, data structures should reveal minimal information beyond their current contents. This is even more crucial for learning-augmented data structures, whose layout adapts to the data. A data structure is history independent if its memory representation reveals no information about past operations except what is inferred from its current contents. In this work, we take the first step towards privacy and security guarantees in this setting by proposing the first learning-augmented data structure that is strongly history independent, robust, and supports dynamic updates. To achieve this, we introduce two techniques: thresholding, which automatically makes any learning-augmented data structure robust, and pairing, a simple technique that provides strong history independence in the dynamic setting. Our experimental results demonstrate a tradeoff between security and efficiency but are still competitive with the state of the art.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00165
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Privacy-Preserving Learning-Augmented Data Structures
Goyal, Prabhav
Sridhar, Vinesh
Zheng, Wilson
Information Retrieval
Artificial Intelligence
Data Structures and Algorithms
Learning-augmented data structures use predicted frequency estimates to retrieve frequently occurring database elements faster than standard data structures. Recent work has developed data structures that optimally exploit these frequency estimates while maintaining robustness to adversarial prediction errors. However, the privacy and security implications of this setting remain largely unexplored. In the event of a security breach, data structures should reveal minimal information beyond their current contents. This is even more crucial for learning-augmented data structures, whose layout adapts to the data. A data structure is history independent if its memory representation reveals no information about past operations except what is inferred from its current contents. In this work, we take the first step towards privacy and security guarantees in this setting by proposing the first learning-augmented data structure that is strongly history independent, robust, and supports dynamic updates. To achieve this, we introduce two techniques: thresholding, which automatically makes any learning-augmented data structure robust, and pairing, a simple technique that provides strong history independence in the dynamic setting. Our experimental results demonstrate a tradeoff between security and efficiency but are still competitive with the state of the art.
title Privacy-Preserving Learning-Augmented Data Structures
topic Information Retrieval
Artificial Intelligence
Data Structures and Algorithms
url https://arxiv.org/abs/2510.00165