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, 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.