Security for Distributed Machine Learning

Laurent Gomez, Tianchi Yu, Patrick Duverger

2023

Abstract

With the adoption of IoT-like technologies, industrials aim to enhance the business value of their physical assets and improve their operational efficiency. However, IoT devices alone tend to strain enterprise systems with a sheer volume of unstructured and unfiltered data. To overcome this challenge, endowing (smart) devices with AI-based capabilities can significantly enhance enterprise system capabilities. However, deploying AI-based capabilities on potentially insecure edge hardware and platforms introduces new security risks, including AI model theft, poisoning, and data leaks. This paradigm shift necessitates the protection of distributed AI applications and data. In this paper, we propose a solution for safeguarding the Intellectual Property and data privacy of ML-based software. We utilize hardware-assisted Privacy Enhancing Technologies, specifically Trusted Execution Environments. We evaluate the effectiveness of our approach in the context of ML-based motion detection in CCTV cameras. This work is part of a co-innovation project with the Smart City of Antibes, France.

Paper Citation

in Harvard Style

Gomez L., Yu T. and Duverger P. (2023). Security for Distributed Machine Learning. In Proceedings of the 20th International Conference on Security and Cryptography - Volume 1: SECRYPT; ISBN 978-989-758-666-8, SciTePress, pages 838-843. DOI: 10.5220/0012137700003555

in Bibtex Style

@conference{secrypt23,
author={Laurent Gomez and Tianchi Yu and Patrick Duverger},
title={Security for Distributed Machine Learning},
booktitle={Proceedings of the 20th International Conference on Security and Cryptography - Volume 1: SECRYPT},
year={2023},
pages={838-843},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012137700003555},
isbn={978-989-758-666-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Security and Cryptography - Volume 1: SECRYPT
TI - Security for Distributed Machine Learning
SN - 978-989-758-666-8
AU - Gomez L.
AU - Yu T.
AU - Duverger P.
PY - 2023
SP - 838
EP - 843
DO - 10.5220/0012137700003555
PB - SciTePress