Information-Theoretically Secure Distributed Machine Learning
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
A previously obscure area of cryptography known as Secure Multiparty Computation (MPC) is enjoying increased attention in the field of privacy-preserving machine learning (ML), because ML models implemented using MPC can be uniquely resistant to capture or reverse engineering by an adversary. In particular, an adversary who captures a share of a distributed MPC model provably cannot recover the model itself, nor data evaluated by the model, even by observing the model in operation. We report on our small project to survey current MPC software and judge its practicality for fielding mission-relevant distributed machine learning models.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- AC04-94AL85000; NA0003525
- OSTI ID:
- 1763277
- Report Number(s):
- SAND--2019-13692; 681291
- Country of Publication:
- United States
- Language:
- English
Similar Records
Adapting Secure MultiParty Computation to Support Machine Learning in Radio Frequency Sensor Networks
Using Machine Learning in Adversarial Environments.
Technical Report
·
Fri Oct 01 00:00:00 EDT 2021
·
OSTI ID:1842271
Using Machine Learning in Adversarial Environments.
Technical Report
·
Sun Jan 31 23:00:00 EST 2016
·
OSTI ID:1238101