Moving target defense for embedded deep visual sensing against adversarial examples

Qun Song, Zhenyu Yan, Rui Tan
{"title":"Moving target defense for embedded deep visual sensing against adversarial examples","authors":"Qun Song, Zhenyu Yan, Rui Tan","doi":"10.1145/3356250.3360025","DOIUrl":null,"url":null,"abstract":"Deep learning-based visual sensing has achieved attractive accuracy but is shown vulnerable to adversarial example attacks. Specifically, once the attackers obtain the deep model, they can construct adversarial examples to mislead the model to yield wrong classification results. Deployable adversarial examples such as small stickers pasted on the road signs and lanes have been shown effective in misleading advanced driver-assistance systems. Many existing countermeasures against adversarial examples build their security on the attackers' ignorance of the defense mechanisms. Thus, they fall short of following Kerckhoffs's principle and can be subverted once the attackers know the details of the defense. This paper applies the strategy of moving target defense (MTD) to generate multiple new deep models after system deployment, that will collaboratively detect and thwart adversarial examples. Our MTD design is based on the adversarial examples' minor transferability across different models. The post-deployment dynamically generated models significantly increase the bar of successful attacks. We also apply serial data fusion with early stopping to reduce the inference time by a factor of up to 5. Evaluation based on four datasets including a road sign dataset and two GPU-equipped Jetson embedded computing platforms shows the effectiveness of our approach.","PeriodicalId":432452,"journal":{"name":"Proceedings of the 17th Conference on Embedded Networked Sensor Systems","volume":"279 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 17th Conference on Embedded Networked Sensor Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3356250.3360025","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12

Abstract

Deep learning-based visual sensing has achieved attractive accuracy but is shown vulnerable to adversarial example attacks. Specifically, once the attackers obtain the deep model, they can construct adversarial examples to mislead the model to yield wrong classification results. Deployable adversarial examples such as small stickers pasted on the road signs and lanes have been shown effective in misleading advanced driver-assistance systems. Many existing countermeasures against adversarial examples build their security on the attackers' ignorance of the defense mechanisms. Thus, they fall short of following Kerckhoffs's principle and can be subverted once the attackers know the details of the defense. This paper applies the strategy of moving target defense (MTD) to generate multiple new deep models after system deployment, that will collaboratively detect and thwart adversarial examples. Our MTD design is based on the adversarial examples' minor transferability across different models. The post-deployment dynamically generated models significantly increase the bar of successful attacks. We also apply serial data fusion with early stopping to reduce the inference time by a factor of up to 5. Evaluation based on four datasets including a road sign dataset and two GPU-equipped Jetson embedded computing platforms shows the effectiveness of our approach.
针对对抗性实例的嵌入式深度视觉传感移动目标防御
基于深度学习的视觉感知已经取得了很好的准确性,但也容易受到对抗性示例攻击。具体来说,一旦攻击者获得了深度模型,他们就可以构造对抗性的样本来误导模型,从而产生错误的分类结果。可部署的对抗性例子,如贴在路标和车道上的小贴纸,已被证明能有效地误导高级驾驶员辅助系统。许多针对对抗性实例的现有对策的安全性建立在攻击者对防御机制的无知之上。因此,它们不符合Kerckhoffs的原则,一旦攻击者知道了防御的细节,它们就会被破坏。本文应用移动目标防御策略(MTD)在系统部署后生成多个新的深度模型,这些模型将协同检测和挫败对抗示例。我们的MTD设计是基于对抗性示例在不同模型之间的次要可转移性。部署后动态生成的模型显著提高了成功攻击的门槛。我们还采用提前停止的串行数据融合,将推理时间减少了5倍。基于四个数据集(包括一个路标数据集和两个配备gpu的Jetson嵌入式计算平台)的评估显示了我们方法的有效性。
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:604180095
Book学术官方微信
小红书