Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Masking Feedforward Neural Networks Against Power Analysis Attacks

Masking Feedforward Neural Networks Against Power Analysis Attacks AbstractRecent advances in machine learning have enabled Neural Network (NN) inference directly on constrained embedded devices. This local approach enhances the privacy of user data, as the inputs to the NN inference are not shared with third-party cloud providers over a communication network. At the same time, however, performing local NN inference on embedded devices opens up the possibility of Power Analysis attacks, which have recently been shown to be effective in recovering NN parameters, as well as their activations and structure. Knowledge of these NN characteristics constitutes a privacy threat, as it enables highly effective Membership Inference and Model Inversion attacks, which can recover information about the sensitive data that the NN model was trained on. In this paper we address the problem of securing sensitive NN inference parameters against Power Analysis attacks. Our approach employs masking, a countermeasure well-studied in the context of cryptographic algorithms. We design a set of gadgets, i.e., masked operations, tailored to NN inference. We prove our proposed gadgets secure against power attacks and show, both formally and experimentally, that they are composable, resulting in secure NN inference. We further propose optimizations that exploit intrinsic characteristics of NN inference to reduce the masking’s runtime and randomness requirements. We empirically evaluate the performance of our constructions, showing them to incur a slowdown by a factor of about 2–5. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Proceedings on Privacy Enhancing Technologies de Gruyter

Masking Feedforward Neural Networks Against Power Analysis Attacks

Download PDF
21 pages

Loading next page...
 
/lp/de-gruyter/masking-feedforward-neural-networks-against-power-analysis-attacks-s0YJ9GalaS

References (56)

Publisher
de Gruyter
Copyright
© 2022 Konstantinos Athanasiou et al., published by Sciendo
ISSN
2299-0984
eISSN
2299-0984
DOI
10.2478/popets-2022-0025
Publisher site
See Article on Publisher Site

Abstract

AbstractRecent advances in machine learning have enabled Neural Network (NN) inference directly on constrained embedded devices. This local approach enhances the privacy of user data, as the inputs to the NN inference are not shared with third-party cloud providers over a communication network. At the same time, however, performing local NN inference on embedded devices opens up the possibility of Power Analysis attacks, which have recently been shown to be effective in recovering NN parameters, as well as their activations and structure. Knowledge of these NN characteristics constitutes a privacy threat, as it enables highly effective Membership Inference and Model Inversion attacks, which can recover information about the sensitive data that the NN model was trained on. In this paper we address the problem of securing sensitive NN inference parameters against Power Analysis attacks. Our approach employs masking, a countermeasure well-studied in the context of cryptographic algorithms. We design a set of gadgets, i.e., masked operations, tailored to NN inference. We prove our proposed gadgets secure against power attacks and show, both formally and experimentally, that they are composable, resulting in secure NN inference. We further propose optimizations that exploit intrinsic characteristics of NN inference to reduce the masking’s runtime and randomness requirements. We empirically evaluate the performance of our constructions, showing them to incur a slowdown by a factor of about 2–5.

Journal

Proceedings on Privacy Enhancing Technologies – de Gruyter

Published: Jan 1, 2022

Keywords: side-channels; neural networks; masking

There are no references for this article.