Clock Glitch Fault Attacks on Deep Neural Networks and Their Countermeasures

Recently, deep neural networks (DNNs) have been widely used in various fields, such as autonomous vehicles and smart homes. Since these DNNs can be directly implemented on edge devices, they offer advantages such as real-time processing in low-power and low-bandwidth environments. However, the deplo...

Full description

Saved in:
Bibliographic Details
Main Authors: Sangwon Lee, Suhyung Kim, Seongwoo Hong, Jaecheol Ha
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2793
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850135704960499712
author Sangwon Lee
Suhyung Kim
Seongwoo Hong
Jaecheol Ha
author_facet Sangwon Lee
Suhyung Kim
Seongwoo Hong
Jaecheol Ha
author_sort Sangwon Lee
collection DOAJ
description Recently, deep neural networks (DNNs) have been widely used in various fields, such as autonomous vehicles and smart homes. Since these DNNs can be directly implemented on edge devices, they offer advantages such as real-time processing in low-power and low-bandwidth environments. However, the deployment of DNNs in embedded systems, including edge devices, exposes them to threats such as fault injection attacks. This paper introduces a method of inducing misclassification using clock glitch fault attacks in devices where DNN models are executed. As a result of experiments on a microcontroller with a DNN implemented for two types of image classification (multi-class and binary classification using MNIST, CIFAR-10, and Kaggle datasets), we show that clock glitch fault attacks can lead—with a high probability—to the occurrence of serious misclassifications. Furthermore, we propose countermeasures to defeat the glitch attacks on each Softmax function and Sigmoid function at the algorithm level, and we confirm that these methods can effectively prevent misclassification incidents.
format Article
id doaj-art-b2be3617c5624c068d2ccd36542d2d0c
institution OA Journals
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b2be3617c5624c068d2ccd36542d2d0c2025-08-20T02:31:20ZengMDPI AGSensors1424-82202025-04-01259279310.3390/s25092793Clock Glitch Fault Attacks on Deep Neural Networks and Their CountermeasuresSangwon Lee0Suhyung Kim1Seongwoo Hong2Jaecheol Ha3Department of Information Security, Hoseo University, Asan-Si 31499, Republic of KoreaDepartment of Information Security, Hoseo University, Asan-Si 31499, Republic of KoreaEV R&D Team, Coontec Co., Ltd., Seongnam-Si 13449, Republic of KoreaDepartment of Information Security, Hoseo University, Asan-Si 31499, Republic of KoreaRecently, deep neural networks (DNNs) have been widely used in various fields, such as autonomous vehicles and smart homes. Since these DNNs can be directly implemented on edge devices, they offer advantages such as real-time processing in low-power and low-bandwidth environments. However, the deployment of DNNs in embedded systems, including edge devices, exposes them to threats such as fault injection attacks. This paper introduces a method of inducing misclassification using clock glitch fault attacks in devices where DNN models are executed. As a result of experiments on a microcontroller with a DNN implemented for two types of image classification (multi-class and binary classification using MNIST, CIFAR-10, and Kaggle datasets), we show that clock glitch fault attacks can lead—with a high probability—to the occurrence of serious misclassifications. Furthermore, we propose countermeasures to defeat the glitch attacks on each Softmax function and Sigmoid function at the algorithm level, and we confirm that these methods can effectively prevent misclassification incidents.https://www.mdpi.com/1424-8220/25/9/2793sensor networkdeep neural networkimage classificationhardware securityfault injection attack
spellingShingle Sangwon Lee
Suhyung Kim
Seongwoo Hong
Jaecheol Ha
Clock Glitch Fault Attacks on Deep Neural Networks and Their Countermeasures
Sensors
sensor network
deep neural network
image classification
hardware security
fault injection attack
title Clock Glitch Fault Attacks on Deep Neural Networks and Their Countermeasures
title_full Clock Glitch Fault Attacks on Deep Neural Networks and Their Countermeasures
title_fullStr Clock Glitch Fault Attacks on Deep Neural Networks and Their Countermeasures
title_full_unstemmed Clock Glitch Fault Attacks on Deep Neural Networks and Their Countermeasures
title_short Clock Glitch Fault Attacks on Deep Neural Networks and Their Countermeasures
title_sort clock glitch fault attacks on deep neural networks and their countermeasures
topic sensor network
deep neural network
image classification
hardware security
fault injection attack
url https://www.mdpi.com/1424-8220/25/9/2793
work_keys_str_mv AT sangwonlee clockglitchfaultattacksondeepneuralnetworksandtheircountermeasures
AT suhyungkim clockglitchfaultattacksondeepneuralnetworksandtheircountermeasures
AT seongwoohong clockglitchfaultattacksondeepneuralnetworksandtheircountermeasures
AT jaecheolha clockglitchfaultattacksondeepneuralnetworksandtheircountermeasures