Privacy-Preserving Network Analytics

58 Pages Posted: 19 Oct 2020 Last revised: 12 Mar 2021

See all articles by Marcella Hastings

Marcella Hastings

University of Pennsylvania - Department of Computer and Information Science

Brett Hemenway Falk

University of Pennsylvania - Department of Computer and Information Science

Gerry Tsoukalas

University of Pennsylvania - The Wharton School

Date Written: March 12, 2021

Abstract

We develop a new privacy-preserving analytics framework for a general class of financial network models, leveraging recent advances in cryptography and decentralized systems (secure multi-party computation). We show how aggregate-level statistics required for stability assessment and stress testing can be derived from real network data, without any individual node revealing its private information to any third party, be it other nodes in the network, or even a central agent. Our work bridges the gap between established theories of financial network contagion and systemic risk, that assume agents have full information, and the real world, where information sharing is hindered by privacy and security concerns.

Keywords: financial networks, multiparty computation, privacy preservation, fintech

JEL Classification: E6, G2, L5, O3, C6

Suggested Citation

Hastings, Marcella and Hemenway Falk, Brett and Tsoukalas, Gerry, Privacy-Preserving Network Analytics (March 12, 2021). Available at SSRN: https://ssrn.com/abstract=3680000 or http://dx.doi.org/10.2139/ssrn.3680000

Marcella Hastings

University of Pennsylvania - Department of Computer and Information Science ( email )

3330 Walnut Street
Philadelphia, PA 19104
United States

Brett Hemenway Falk

University of Pennsylvania - Department of Computer and Information Science ( email )

3330 Walnut Street
Philadelphia, PA 19104
United States

Gerry Tsoukalas (Contact Author)

University of Pennsylvania - The Wharton School ( email )

3641 Locust Walk
Philadelphia, PA 19104-6365
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
129
Abstract Views
663
rank
269,225
PlumX Metrics