物联网中对抗性机器学习攻击的分类与分析:标签翻转攻击案例研究

M. Abrishami, S. Dadkhah, E. P. Neto, Pulei Xiong, Shahrear Iqbal, S. Ray, A. Ghorbani
{"title":"物联网中对抗性机器学习攻击的分类与分析:标签翻转攻击案例研究","authors":"M. Abrishami, S. Dadkhah, E. P. Neto, Pulei Xiong, Shahrear Iqbal, S. Ray, A. Ghorbani","doi":"10.23919/FRUCT56874.2022.9953823","DOIUrl":null,"url":null,"abstract":"With the increased usage of Internet of Things (IoT) devices in recent years, various Machine Learning (ML) algorithms have also developed dramatically for attack detection in this domain. However, the ML models are exposed to different classes of adversarial attacks that aim to fool a model into making an incorrect prediction. For instance, label manipulation or label flipping is an adversarial attack where the adversary attempts to manipulate the label of training data that causes the trained model biased and/or with decreased performance. However, the number of samples to be flipped in this category of attack can be restricted, giving the attacker a limited target selection. Due to the great significance of securing ML models against Adversarial Machine Learning (AML) attacks particularly in the IoT domain, this research presents an extensive review of AML in IoT. Then, a classification of AML attacks is presented based on the literature which sheds light on the future research in this domain. Next, this paper investigates the negative impact levels of applying the malicious label-flipping attacks on IoT data. We devise label-flipping scenarios for training a Support Vector Machine (SVM) model. The experiments demonstrate that the label flipping attacks impact the performance of ML models. These results can lead to designing more effective and powerful attack and defense mechanisms in adversarial settings. Finally, we show the weaknesses of the K-NN defense method against the random label flipping attack.","PeriodicalId":274664,"journal":{"name":"2022 32nd Conference of Open Innovations Association (FRUCT)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Classification and Analysis of Adversarial Machine Learning Attacks in IoT: a Label Flipping Attack Case Study\",\"authors\":\"M. Abrishami, S. Dadkhah, E. P. Neto, Pulei Xiong, Shahrear Iqbal, S. Ray, A. Ghorbani\",\"doi\":\"10.23919/FRUCT56874.2022.9953823\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"With the increased usage of Internet of Things (IoT) devices in recent years, various Machine Learning (ML) algorithms have also developed dramatically for attack detection in this domain. However, the ML models are exposed to different classes of adversarial attacks that aim to fool a model into making an incorrect prediction. For instance, label manipulation or label flipping is an adversarial attack where the adversary attempts to manipulate the label of training data that causes the trained model biased and/or with decreased performance. However, the number of samples to be flipped in this category of attack can be restricted, giving the attacker a limited target selection. Due to the great significance of securing ML models against Adversarial Machine Learning (AML) attacks particularly in the IoT domain, this research presents an extensive review of AML in IoT. Then, a classification of AML attacks is presented based on the literature which sheds light on the future research in this domain. Next, this paper investigates the negative impact levels of applying the malicious label-flipping attacks on IoT data. We devise label-flipping scenarios for training a Support Vector Machine (SVM) model. The experiments demonstrate that the label flipping attacks impact the performance of ML models. These results can lead to designing more effective and powerful attack and defense mechanisms in adversarial settings. Finally, we show the weaknesses of the K-NN defense method against the random label flipping attack.\",\"PeriodicalId\":274664,\"journal\":{\"name\":\"2022 32nd Conference of Open Innovations Association (FRUCT)\",\"volume\":\"55 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 32nd Conference of Open Innovations Association (FRUCT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23919/FRUCT56874.2022.9953823\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 32nd Conference of Open Innovations Association (FRUCT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/FRUCT56874.2022.9953823","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

近年来,随着物联网(IoT)设备的使用越来越多,各种机器学习(ML)算法也在该领域的攻击检测中得到了极大的发展。然而,ML模型暴露于不同类别的对抗性攻击,这些攻击旨在欺骗模型做出错误的预测。例如,标签操纵或标签翻转是一种对抗性攻击,攻击者试图操纵训练数据的标签,从而导致训练模型有偏差和/或性能下降。然而,在这类攻击中要翻转的样本数量是有限制的,这给了攻击者一个有限的目标选择。由于保护ML模型免受对抗性机器学习(AML)攻击的重要意义,特别是在物联网领域,本研究对物联网中的AML进行了广泛的回顾。然后,在文献的基础上提出了AML攻击的分类,为该领域的未来研究提供了启示。接下来,本文研究了应用恶意标签翻转攻击对物联网数据的负面影响程度。我们设计了标签翻转场景来训练支持向量机(SVM)模型。实验表明,标签翻转攻击会影响机器学习模型的性能。这些结果可以引导我们在对抗环境中设计更有效和强大的攻击和防御机制。最后,我们展示了K-NN防御方法对抗随机标签翻转攻击的弱点。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Classification and Analysis of Adversarial Machine Learning Attacks in IoT: a Label Flipping Attack Case Study
With the increased usage of Internet of Things (IoT) devices in recent years, various Machine Learning (ML) algorithms have also developed dramatically for attack detection in this domain. However, the ML models are exposed to different classes of adversarial attacks that aim to fool a model into making an incorrect prediction. For instance, label manipulation or label flipping is an adversarial attack where the adversary attempts to manipulate the label of training data that causes the trained model biased and/or with decreased performance. However, the number of samples to be flipped in this category of attack can be restricted, giving the attacker a limited target selection. Due to the great significance of securing ML models against Adversarial Machine Learning (AML) attacks particularly in the IoT domain, this research presents an extensive review of AML in IoT. Then, a classification of AML attacks is presented based on the literature which sheds light on the future research in this domain. Next, this paper investigates the negative impact levels of applying the malicious label-flipping attacks on IoT data. We devise label-flipping scenarios for training a Support Vector Machine (SVM) model. The experiments demonstrate that the label flipping attacks impact the performance of ML models. These results can lead to designing more effective and powerful attack and defense mechanisms in adversarial settings. Finally, we show the weaknesses of the K-NN defense method against the random label flipping attack.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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:604180095
Book学术官方微信