CryptoDB
Pancake: Frequency Smoothing for Encrypted Data Stores
| Authors: | |
|---|---|
| Download: | |
| Abstract: | In this talk I will present the design, analysis, and implementation of Pancake, the first system to protect key-value stores from access pattern leakage attacks with small constant factor bandwidth overhead. First, I will outline our new formal security model, and explain why it captures realistic attacks. Then, I will describe our frequency smoothing mechanism, which provably transforms plaintext accesses into uniformly-distributed encrypted accesses. Finally, I will explain the implementation and evaluation of the Pancake system itself. We integrated Pancake into three key-value stores used in production clusters, and demonstrated its practicality: on standard benchmarks, PANCAKE achieves 229× better throughput than non-recursive Path ORAM - within 3-6× of insecure baselines for these key-value stores. |
| Video: | https://youtu.be/CiH6iqjWpt8?t=2090 |
BibTeX
@misc{rwc-2021-35550,
title={Pancake: Frequency Smoothing for Encrypted Data Stores},
note={Video at \url{https://youtu.be/CiH6iqjWpt8?t=2090}},
howpublished={Talk given at RWC 2021},
author={Paul Grubbs and Anurag Khandelwal and Marie-Sarah Lacharité and Lloyd Brown and Lucy Li and Rachit Agarwal and Thomas Ristenpart},
year=2021
}