Object detection systems are used in various fields such as autonomous vehicles and facial recognition. In particular, object detection using deep learning networks enables real-time processing in low-performance edge devices and can maintain high detection rates. However, edge devices that operate far from administrators are vulnerable to various physical attacks by malicious adversaries. In this paper, we implement a function for detecting traffic signs by using You Only Look Once (YOLO) as well as Faster-RCNN, which can be adopted by edge devices of autonomous vehicles. Then, assuming the role of a malicious attacker, we executed adversarial patch attacks with Adv-Patch and Dpatch. Trying to cause misdetection of traffic stop signs by using Adv-Patch and Dpatch, we confirmed the attacks can succeed with a high probability. To defeat these attacks, we propose an image reconstruction method using an autoencoder and the Structural Similarity Index Measure (SSIM). We confirm that the proposed method can sufficiently defend against an attack, attaining a mean Average Precision (mAP) of 91.46% even when two adversarial attacks are launched.

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.

Object detection systems are widely used in various fields such as autonomous vehicles and facial recognition. In particular, object detection using deep learning networks enables real-time processing in low-performance edge devices, and can maintain high detection rates. However, edge devices that operate far from administrators are vulnerable to various physical attacks by malicious adversaries. In this paper, we implement a function for detecting traffic signs by using three versions of You Only Look Once (YOLO) and Faster-RCNN, which can be adopted by edge devices of autonomous vehicles. Then, assuming the role of a malicious attacker, we executed adversarial patch attacks with Adv-Patch and Dpatch. As a result of experimenting with misdetection of traffic stop signs using Adv-Patch and Dpatch, we confirmed the attacks can succeed with a high probability. To defeat these attacks, we propose an image reconstruction method using an autoencoder and the Structural Similarity Index Measure (SSIM). We confirm that the proposed method can sufficiently defend against an attack, attaining an AP above 91.46% even when two adversarial attacks are launched.

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.