Fundamental Study of Adversarial Examples Created by Fault Injection Attack on Image Sensor Interface

Tatsuya Oyama, Kota Yoshida, S. Okura, T. Fujino
{"title":"Fundamental Study of Adversarial Examples Created by Fault Injection Attack on Image Sensor Interface","authors":"Tatsuya Oyama, Kota Yoshida, S. Okura, T. Fujino","doi":"10.1109/AsianHOST56390.2022.10022189","DOIUrl":null,"url":null,"abstract":"Adversarial examples (AEs), which cause misclassification by adding subtle perturbations to input images, have been proposed as an attack method on image classification systems using deep neural networks (DNNs). Physical AEs created by attaching stickers to traffic signs have been reported, which are a threat against the traffic-sign-recognition DNNs used in advanced driver assistance systems (ADAS). We previously proposed an attack method that generates a noise area on images by superimposing an electrical signal on the mobile industry processor interface (MIPI) and showed that it can generate a single adversarial mark that triggers a backdoor attack on the input image. As the advanced approach, we propose the targeted misclassification attack method on DNN by the AEs which are generated by small perturbations to various places on the image by the fault injection. The perturbation position for AEs is precalculated in advance against the target traffic-sign image, which will be captured on future driving. The perturbation image (5.2-5.5% area is tampered with) is successfully created by the fault injection attack on MIPI, which is connected to Raspberry Pi. As the experimental results, we confirmed that the traffic-sign-recognition DNN on a Raspberry Pi was successfully misclassified when the target traffic sign was captured.","PeriodicalId":207435,"journal":{"name":"2022 Asian Hardware Oriented Security and Trust Symposium (AsianHOST)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 Asian Hardware Oriented Security and Trust Symposium (AsianHOST)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AsianHOST56390.2022.10022189","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Adversarial examples (AEs), which cause misclassification by adding subtle perturbations to input images, have been proposed as an attack method on image classification systems using deep neural networks (DNNs). Physical AEs created by attaching stickers to traffic signs have been reported, which are a threat against the traffic-sign-recognition DNNs used in advanced driver assistance systems (ADAS). We previously proposed an attack method that generates a noise area on images by superimposing an electrical signal on the mobile industry processor interface (MIPI) and showed that it can generate a single adversarial mark that triggers a backdoor attack on the input image. As the advanced approach, we propose the targeted misclassification attack method on DNN by the AEs which are generated by small perturbations to various places on the image by the fault injection. The perturbation position for AEs is precalculated in advance against the target traffic-sign image, which will be captured on future driving. The perturbation image (5.2-5.5% area is tampered with) is successfully created by the fault injection attack on MIPI, which is connected to Raspberry Pi. As the experimental results, we confirmed that the traffic-sign-recognition DNN on a Raspberry Pi was successfully misclassified when the target traffic sign was captured.
图像传感器接口故障注入攻击生成对抗实例的基础研究
对抗性示例(AEs)是一种利用深度神经网络(dnn)攻击图像分类系统的方法,它通过在输入图像中添加细微的扰动而导致误分类。有报道称,在交通标志上贴贴纸产生的物理ae对高级驾驶辅助系统(ADAS)中使用的交通标志识别dnn构成威胁。我们之前提出了一种攻击方法,该方法通过在移动工业处理器接口(MIPI)上叠加电信号在图像上产生噪声区域,并表明它可以产生单个对抗性标记,从而触发对输入图像的后门攻击。作为一种先进的方法,我们提出了利用断层注入对图像上不同位置的小扰动产生的ae对深度神经网络进行针对性误分类攻击的方法。针对目标交通标志图像,预先计算ae的摄动位置,并在以后的驾驶中捕获。通过对连接树莓派的MIPI进行故障注入攻击,成功创建了扰动图像(5.2-5.5%区域被篡改)。作为实验结果,我们证实了树莓派上的交通标志识别DNN在捕获目标交通标志时成功地进行了错误分类。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信