NDSS 2025 – Recurrent Private Set Intersection For Unbalanced Databases With Cuckoo Hashing
好的，我现在需要帮用户总结一篇文章的内容，控制在100个字以内。首先，我得仔细阅读文章，抓住主要信息。
文章标题是“Recurrent Private Set Intersection for Unbalanced Databases with Cuckoo Hashing and Leveled FHE”。看起来是关于隐私保护的，特别是集合交集的协议。作者来自纽约大学阿布扎比分校。
内容方面，文章讨论了现有的PSI协议在处理不平衡数据库时效率低下的问题。他们提出了一个优化的协议，使用了Cuckoo哈希和Leveled FHE技术，并且进行了优化以实现实时性能。实验结果显示，在不同网络环境下，他们的协议比现有方案快了一个或两个数量级。
用户的要求是用中文总结，不超过100字，不需要特定开头。我需要简洁明了地表达这些关键点：提出新协议、针对不平衡数据库、使用的技术、性能提升。
可能的结构：研究提出了一种新的PSI协议，用于处理不平衡数据库，在慢速和快速网络下分别提升了10倍和100倍的速度。
检查字数是否符合要求，确保信息准确无误。
</think>
研究提出了一种新的私密集合交集（PSI）协议，针对不平衡数据库设计优化，并结合Cuckoo哈希和Leveled FHE技术，在慢速和快速网络下分别将交集时间缩短了一个和两个数量级。
2026-1-28 20:0:0
Author: securityboulevard.com(查看原文)
阅读量:0
收藏
Session 10C: Privacy Preservation
Authors, Creators & Presenters: Eduardo Chielle (New York University Abu Dhabi), Michail Maniatakos (New York University Abu Dhabi)
PAPER
Recurrent Private Set Intersection for Unbalanced Databases with Cuckoo Hashing and Leveled FHE
A Private Set Intersection (PSI) protocol is a cryptographic method allowing two parties, each with a private set, to determine the intersection of their sets without revealing any information about their entries except for the intersection itself. While extensive research has focused on PSI protocols, most studies have centered on scenarios where two parties possess sets of similar sizes, assuming a semi-honest threat model. However, when the sizes of the parties’ sets differ significantly, a generalized solution tends to underperform compared to a specialized one, as recent research has demonstrated. Additionally, conventional PSI protocols are typically designed for a single execution, requiring the entire protocol to be re-executed for each set intersection. This approach is suboptimal for applications such as URL denylisting and email filtering, which may involve multiple set intersections of small sets against a large set (e.g., one for each email received). In this study, we propose a novel PSI protocol optimized for the recurrent setting where parties have unbalanced set sizes. We implement our protocol using Levelled Fully Homomorphic Encryption and Cuckoo hashing, and introduce several optimizations to ensure real-time performance. By utilizing the Microsoft SEAL library, we demonstrate that our protocol can perform private set intersections in 20 ms and 240 ms on 10 Gbps and 100 Mbps networks, respectively. Compared to existing solutions, our protocol offers significant improvements, reducing set intersection times by one order of magnitude on slower networks and by two orders of magnitude on faster networks.
ABOUT NDSS
The Network and Distributed System Security Symposium (NDSS) fosters information exchange among researchers and practitioners of network and distributed system security. The target audience includes those interested in practical aspects of network and distributed system security, with a focus on actual system design and implementation. A major goal is to encourage and enable the Internet community to apply, deploy, and advance the state of available security technologies.
