A Countermeasure to Glitch-based Fault Injection Attacks on Deep Neural Networks
Preprint
- 4 September 2024
- preprint
- Published by MDPI AG in Preprints.org
Abstract
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, deployment of DNNs in embedded systems, including edge devices, exposes them to threats such as fault injection attacks. In this paper, we introduce two methods to induce misclassifications by using clock and voltage glitch-based fault attacks in devices where DNN models are executed. As a result of experiments on a microcontroller implemented with a DNN for image classification, we show that glitch injection attacks can lead with high probability to serious misclassifications. Furthermore, we propose a countermeasure to glitch attacks on the softmax function, and confirm that this method is effective in preventing misclassifications.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- RAM-Jam: Remote Temperature and Voltage Fault Attack on FPGAs using Memory Collisions2019
- Mitigating Reverse Engineering Attacks on Deep Neural Networks2019
- Practical Fault Attack on Deep Neural Networks2018
- Threat of Adversarial Attacks on Deep Learning in Computer Vision: A SurveyIEEE Access, 2018
- Fault injection attack on deep neural network2017
- Laser Profiling for the Back-Side Fault Attacks2015
- When Clocks Fail: On Critical Paths and Clock Faults2010
- Low Voltage Fault Attacks on the RSA Cryptosystem2009
- On the Importance of Checking Cryptographic Protocols for Faults1997
- Differential fault analysis of secret key cryptosystems1997