On the Practicality of Dynamic Updates in Fast Searchable Encryption

TL;DR

This paper presents a practical, real-world implementation of dynamic searchable encrypted indexing, demonstrating its feasibility and performance, and bridging the gap between theoretical models and real-world applications.

Contribution

Developed the first empirical, end-to-end dynamic searchable encryption system with practical update capabilities and performance evaluation.

Findings

Successful implementation of dynamic SE updates in a real-world system

Performance metrics demonstrating viability for practical use

Identification of challenges for future optimization

Abstract

Searchable encrypted (SE) indexing systems are a useful tool for utilizing cloud services to store and manage sensitive information. However, much of the work on SE systems to date has remained theoretical. In order to make them of practical use, more work is needed to develop optimal protocols and working models for them. This includes, in particular, the creation of a working update model in order to maintain an encrypted index of a dynamic document set such as an email inbox. I have created a working, real-world end-to-end SE implementation that satisfies these needs, including the first empirical performance evaluation of the dynamic SE update operation. In doing so, I show a viable path to move from the theoretical concepts described by previous researchers to a future production-worthy implementation and identify issues for follow-on investigation.