Trade offs between privacy and communication in shared key storage

Communication and Privacy Trade-Offs in Distributed Storage With Shared Secret Keys

Information Theory

Summary

This work looks at how to store data securely across multiple servers when all communication happens over public channels. The challenge is to let some groups of servers access the file while keeping it mostly private from smaller groups that might try to snoop. The authors examine how the length of secret keys shared individually with servers affects both the privacy level and the maximum file size that can be stored safely. They also figure out the least amount of randomness, communication, and storage needed to achieve the best balance between privacy and efficiency.

What this means in practice

  • For cloud storage providers: Design storage systems that store files securely despite public communication channels using shared secret keys and optimize the balance between privacy and file size.
  • For enterprise security teams: Implement distributed file storage with tunable privacy levels that limit data leakage from colluding internal servers over insecure networks.

Authors

Maryam Keshvari, Remi A. Chou

Abstract

We study distributed storage over public communication channels where privacy is realized using shared secret keys. Specifically, a user wishes to store a file across $L$ servers such that any subset of at least $t$ servers can reconstruct the file, while any subset of at most $z$ colluding servers learns no more than a fraction $α$ of the file. Unlike classical secret-sharing models that assume secure communication channels between the user and each server, we consider a setting where all transmissions occur over a public channel and the user shares an individual secret key of length $n$ bits with each server. For a fixed key length $n$, we characterize the trade-off between the privacy leakage parameter $α$ and the maximum file size that can be securely stored. Additionally, we determine the minimum local randomness, public communication, and storage required to achieve this optimal trade-off.