• search hit 5 of 9
Back to Result List

Offline Model Guard

  • 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 MicrocontrollersPerforming 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.show moreshow less

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:SebastianP Bayerl, Tommaso Frasetto, Patrick Jauernig, Korbinian Riedhammer, Ahmad-Reza Sadeghi, Thomas Schneider, Emmanuel Stapf, Christian Weinert
DOI:https://doi.org/https://doi.org/10.48550/arXiv.2007.02351
ArXiv Id:http://arxiv.org/abs/arXiv:2007.02351
Subtitle (English):Secure and Private ML on Mobile Devices
Document Type:conference proceeding (article)
Language:English
Date of first Publication:2020/07/05
Reviewed:Begutachtet/Reviewed
Release Date:2024/07/05
Tag:TEE, TrustZone, private ML, speech processing
Pagenumber:6
Konferenzangabe:Proc. ACM SIGDA Conference on Design, Automation and Test in Europe (DATE)
institutes:Fakultät Informatik
Licence (German):Keine Lizenz - Deutsches Urheberrecht gilt
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.