Evaluating Privacy Leakage in Split Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Xinchi, Leontiadis, Ilias, Melis, Luca, Sablayrolles, Alex, Stock, Pierre
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909077650538496
author Qiu, Xinchi
Leontiadis, Ilias
Melis, Luca
Sablayrolles, Alex
Stock, Pierre
author_facet Qiu, Xinchi
Leontiadis, Ilias
Melis, Luca
Sablayrolles, Alex
Stock, Pierre
contents Privacy-Preserving machine learning (PPML) can help us train and deploy models that utilize private information. In particular, on-device machine learning allows us to avoid sharing raw data with a third-party server during inference. On-device models are typically less accurate when compared to their server counterparts due to the fact that (1) they typically only rely on a small set of on-device features and (2) they need to be small enough to run efficiently on end-user devices. Split Learning (SL) is a promising approach that can overcome these limitations. In SL, a large machine learning model is divided into two parts, with the bigger part residing on the server side and a smaller part executing on-device, aiming to incorporate the private features. However, end-to-end training of such models requires exchanging gradients at the cut layer, which might encode private features or labels. In this paper, we provide insights into potential privacy risks associated with SL. Furthermore, we also investigate the effectiveness of various mitigation strategies. Our results indicate that the gradients significantly improve the attackers' effectiveness in all tested datasets reaching almost perfect reconstruction accuracy for some features. However, a small amount of differential privacy (DP) can effectively mitigate this risk without causing significant training degradation.
format Preprint
id arxiv_https___arxiv_org_abs_2305_12997
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Evaluating Privacy Leakage in Split Learning
Qiu, Xinchi
Leontiadis, Ilias
Melis, Luca
Sablayrolles, Alex
Stock, Pierre
Machine Learning
Artificial Intelligence
Cryptography and Security
Privacy-Preserving machine learning (PPML) can help us train and deploy models that utilize private information. In particular, on-device machine learning allows us to avoid sharing raw data with a third-party server during inference. On-device models are typically less accurate when compared to their server counterparts due to the fact that (1) they typically only rely on a small set of on-device features and (2) they need to be small enough to run efficiently on end-user devices. Split Learning (SL) is a promising approach that can overcome these limitations. In SL, a large machine learning model is divided into two parts, with the bigger part residing on the server side and a smaller part executing on-device, aiming to incorporate the private features. However, end-to-end training of such models requires exchanging gradients at the cut layer, which might encode private features or labels. In this paper, we provide insights into potential privacy risks associated with SL. Furthermore, we also investigate the effectiveness of various mitigation strategies. Our results indicate that the gradients significantly improve the attackers' effectiveness in all tested datasets reaching almost perfect reconstruction accuracy for some features. However, a small amount of differential privacy (DP) can effectively mitigate this risk without causing significant training degradation.
title Evaluating Privacy Leakage in Split Learning
topic Machine Learning
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2305.12997