Remove Some Noise: On Pre-processing of Side-channel Measurements with Autoencoders
In the profiled side-channel analysis, deep learning-based techniques proved to be very successful even when attacking targets protected with countermeasures. Still, there is no guarantee that deep learning attacks will always succeed. Various countermeasures make attacks significantly more complex...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Ruhr-Universität Bochum
2020-08-01
|
Series: | Transactions on Cryptographic Hardware and Embedded Systems |
Subjects: | |
Online Access: | https://tches.iacr.org/index.php/TCHES/article/view/8688 |
id |
doaj-e889e08b3fbc40e9a2681aead4b3faa8 |
---|---|
record_format |
Article |
spelling |
doaj-e889e08b3fbc40e9a2681aead4b3faa82020-11-25T03:51:34ZengRuhr-Universität BochumTransactions on Cryptographic Hardware and Embedded Systems2569-29252020-08-012020410.13154/tches.v2020.i4.389-415Remove Some Noise: On Pre-processing of Side-channel Measurements with AutoencodersLichao Wu0Stjepan Picek1Delft University of Technology, The NetherlandsDelft University of Technology, The Netherlands In the profiled side-channel analysis, deep learning-based techniques proved to be very successful even when attacking targets protected with countermeasures. Still, there is no guarantee that deep learning attacks will always succeed. Various countermeasures make attacks significantly more complex, and such countermeasures can be further combined to make the attacks even more challenging. An intuitive solution to improve the performance of attacks would be to reduce the effect of countermeasures. This paper investigates whether we can consider certain types of hiding countermeasures as noise and then use a deep learning technique called the denoising autoencoder to remove that noise. We conduct a detailed analysis of six different types of noise and countermeasures separately or combined and show that denoising autoencoder improves the attack performance significantly. https://tches.iacr.org/index.php/TCHES/article/view/8688side-channel analysisDeep learningNoiseCountermeasuresDenoising autoencoder |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lichao Wu Stjepan Picek |
spellingShingle |
Lichao Wu Stjepan Picek Remove Some Noise: On Pre-processing of Side-channel Measurements with Autoencoders Transactions on Cryptographic Hardware and Embedded Systems side-channel analysis Deep learning Noise Countermeasures Denoising autoencoder |
author_facet |
Lichao Wu Stjepan Picek |
author_sort |
Lichao Wu |
title |
Remove Some Noise: On Pre-processing of Side-channel Measurements with Autoencoders |
title_short |
Remove Some Noise: On Pre-processing of Side-channel Measurements with Autoencoders |
title_full |
Remove Some Noise: On Pre-processing of Side-channel Measurements with Autoencoders |
title_fullStr |
Remove Some Noise: On Pre-processing of Side-channel Measurements with Autoencoders |
title_full_unstemmed |
Remove Some Noise: On Pre-processing of Side-channel Measurements with Autoencoders |
title_sort |
remove some noise: on pre-processing of side-channel measurements with autoencoders |
publisher |
Ruhr-Universität Bochum |
series |
Transactions on Cryptographic Hardware and Embedded Systems |
issn |
2569-2925 |
publishDate |
2020-08-01 |
description |
In the profiled side-channel analysis, deep learning-based techniques proved to be very successful even when attacking targets protected with countermeasures. Still, there is no guarantee that deep learning attacks will always succeed. Various countermeasures make attacks significantly more complex, and such countermeasures can be further combined to make the attacks even more challenging. An intuitive solution to improve the performance of attacks would be to reduce the effect of countermeasures.
This paper investigates whether we can consider certain types of hiding countermeasures as noise and then use a deep learning technique called the denoising autoencoder to remove that noise. We conduct a detailed analysis of six different types of noise and countermeasures separately or combined and show that denoising autoencoder improves the attack performance significantly.
|
topic |
side-channel analysis Deep learning Noise Countermeasures Denoising autoencoder |
url |
https://tches.iacr.org/index.php/TCHES/article/view/8688 |
work_keys_str_mv |
AT lichaowu removesomenoiseonpreprocessingofsidechannelmeasurementswithautoencoders AT stjepanpicek removesomenoiseonpreprocessingofsidechannelmeasurementswithautoencoders |
_version_ |
1724486772993294336 |