Detecting Adversarial Attacks In Time-Series Data

Mubarak G. Abdu-Aguye, W. Gomaa, Yasushi Makihara, Y. Yagi
{"title":"Detecting Adversarial Attacks In Time-Series Data","authors":"Mubarak G. Abdu-Aguye, W. Gomaa, Yasushi Makihara, Y. Yagi","doi":"10.1109/ICASSP40776.2020.9053311","DOIUrl":null,"url":null,"abstract":"In recent times, deep neural networks have seen increased adoption in highly critical tasks. They are also susceptible to adversarial attacks, which are specifically crafted changes made to input samples which lead to erroneous output from such models. Such attacks have been shown to affect different types of data such as images and more recently, time-series data. Such susceptibility could have catastrophic consequences, depending on the domain.We propose a method for detecting Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM) adversarial attacks as adapted for time-series data. We frame the problem as an instance of outlier detection and construct a normalcy model based on information and chaos-theoretic measures, which can then be used to determine whether unseen samples are normal or adversarial. Our approach shows promising performance on several datasets from the 2015 UCR Time Series Archive, reaching up to 97% detection accuracy in the best case.","PeriodicalId":13127,"journal":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"16 1","pages":"3092-3096"},"PeriodicalIF":0.0000,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP40776.2020.9053311","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11

Abstract

In recent times, deep neural networks have seen increased adoption in highly critical tasks. They are also susceptible to adversarial attacks, which are specifically crafted changes made to input samples which lead to erroneous output from such models. Such attacks have been shown to affect different types of data such as images and more recently, time-series data. Such susceptibility could have catastrophic consequences, depending on the domain.We propose a method for detecting Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM) adversarial attacks as adapted for time-series data. We frame the problem as an instance of outlier detection and construct a normalcy model based on information and chaos-theoretic measures, which can then be used to determine whether unseen samples are normal or adversarial. Our approach shows promising performance on several datasets from the 2015 UCR Time Series Archive, reaching up to 97% detection accuracy in the best case.
检测时间序列数据中的对抗性攻击
近年来,深度神经网络在高度关键的任务中得到越来越多的应用。它们也容易受到对抗性攻击,对抗性攻击是对输入样本进行的精心设计的更改,从而导致此类模型的错误输出。这种攻击已经被证明可以影响不同类型的数据,比如图像,最近还可以影响时间序列数据。这种易感性可能会产生灾难性的后果,这取决于领域。我们提出了一种检测快速梯度符号法(FGSM)和基本迭代法(BIM)对抗性攻击的方法,该方法适用于时间序列数据。我们将该问题作为离群值检测的一个实例,并基于信息和混沌理论度量构建了一个正态模型,该模型可用于确定看不见的样本是正常的还是敌对的。我们的方法在2015年UCR时间序列存档的几个数据集上显示出了很好的性能,在最好的情况下达到了97%的检测准确率。
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