Paper 2023/1120

TVA: A multi-party computation system for secure and expressive time series analytics

Muhammad Faisal, Boston University
Jerry Zhang, University of California, San Diego
John Liagouris, Boston University
Vasiliki Kalavri, Boston University
Mayank Varia, Boston University
Abstract

We present TVA, a multi-party computation (MPC) system for secure analytics on secret-shared time series data. TVA achieves strong security guarantees in the semi-honest and malicious settings, and high expressivity by enabling complex analytics on inputs with unordered and irregular timestamps. TVA is the first system to support arbitrary composition of oblivious window operators, keyed aggregations, and multiple filter predicates, while keeping all data attributes private, including record timestamps and user-defined values in query predicates. At the core of the TVA system lie novel protocols for secure window assignment: (i) a tumbling window protocol that groups records into fixed-length time buckets and (ii) two session window protocols that identify periods of activity followed by periods of inactivity. We also contribute a new protocol for secure division with a public divisor, which may be of independent interest. We evaluate TVA on real LAN and WAN environments and show that it can efficiently compute complex window-based analytics on inputs of $2^{22}$ records with modest use of resources. When compared to the state-of-the-art, TVA achieves up to $5.8\times$ lower latency in queries with multiple filters and two orders of magnitude better performance in window aggregation.

Metadata
Available format(s)
PDF
Category
Applications
Publication info
Published elsewhere. Major revision. USENIX Security 2023
Keywords
multi-party computationsecure data analyticstine series
Contact author(s)
mfaisal @ bu edu
jerryzhang @ ucsd edu
liagos @ bu edu
vkalavri @ bu edu
varia @ bu edu
History
2023-07-24: approved
2023-07-19: received
See all versions
Short URL
https://ia.cr/2023/1120
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2023/1120,
      author = {Muhammad Faisal and Jerry Zhang and John Liagouris and Vasiliki Kalavri and Mayank Varia},
      title = {{TVA}: A multi-party computation system for secure and expressive time series analytics},
      howpublished = {Cryptology {ePrint} Archive, Paper 2023/1120},
      year = {2023},
      url = {https://eprint.iacr.org/2023/1120}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.