Offline Model Guard: Secure and Private ML on Mobile Devices

Performing machine learning tasks in mobile applications yields a challenging conflict of interest: highly sensitive client information (e.g., speech data) should remain private while also the intellectual property of service providers (e.g., model parameters) must be protected. Cryptographic techni...

Full description

Saved in:
Bibliographic Details
Main Authors: Bayerl, Sebastian P., Frassetto, Tommaso, Jauernig, Patrick, Riedhammer, Korbinian, Sadeghi, Ahmad-Reza, Schneider, Thomas, Stapf, Emmanuel, Weinert, Christian
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
Cryptography
Data models
Mobile handsets
Performance evaluation
private ML
Servers
speech processing
Task analysis
TEE
TrustZone
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Performing machine learning tasks in mobile applications yields a challenging conflict of interest: highly sensitive client information (e.g., speech data) should remain private while also the intellectual property of service providers (e.g., model parameters) must be protected. Cryptographic techniques offer secure solutions for this, but have an unacceptable overhead and moreover require frequent network interaction.In this work, we design a practically efficient hardware-based solution. Specifically, we build OFFLINE MODEL GUARD (OMG) to enable privacy-preserving machine learning on the predominant mobile computing platform ARM-even in offline scenarios. By leveraging a trusted execution environment for strict hardware-enforced isolation from other system components, OMG guarantees privacy of client data, secrecy of provided models, and integrity of processing algorithms. Our prototype implementation on an ARM HiKey 960 development board performs privacy-preserving keyword recognition using TensorFlow Lite for Microcontrollers in real time.
ISSN:1558-1101
DOI:10.23919/DATE48585.2020.9116560