评估深度学习模型应对对抗性攻击的鲁棒性:利用 FGSM、PGD 和 CW 进行分析

W. Villegas-Ch., Ángel Jaramillo-Alcázar, Sergio Luján-Mora
{"title":"评估深度学习模型应对对抗性攻击的鲁棒性:利用 FGSM、PGD 和 CW 进行分析","authors":"W. Villegas-Ch., Ángel Jaramillo-Alcázar, Sergio Luján-Mora","doi":"10.3390/bdcc8010008","DOIUrl":null,"url":null,"abstract":"This study evaluated the generation of adversarial examples and the subsequent robustness of an image classification model. The attacks were performed using the Fast Gradient Sign method, the Projected Gradient Descent method, and the Carlini and Wagner attack to perturb the original images and analyze their impact on the model’s classification accuracy. Additionally, image manipulation techniques were investigated as defensive measures against adversarial attacks. The results highlighted the model’s vulnerability to conflicting examples: the Fast Gradient Signed Method effectively altered the original classifications, while the Carlini and Wagner method proved less effective. Promising approaches such as noise reduction, image compression, and Gaussian blurring were presented as effective countermeasures. These findings underscore the importance of addressing the vulnerability of machine learning models and the need to develop robust defenses against adversarial examples. This article emphasizes the urgency of addressing the threat posed by harmful standards in machine learning models, highlighting the relevance of implementing effective countermeasures and image manipulation techniques to mitigate the effects of adversarial attacks. These efforts are crucial to safeguarding model integrity and trust in an environment marked by constantly evolving hostile threats. An average 25% decrease in accuracy was observed for the VGG16 model when exposed to the Fast Gradient Signed Method and Projected Gradient Descent attacks, and an even more significant 35% decrease with the Carlini and Wagner method.","PeriodicalId":505155,"journal":{"name":"Big Data and Cognitive Computing","volume":" 15","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evaluating the Robustness of Deep Learning Models against Adversarial Attacks: An Analysis with FGSM, PGD and CW\",\"authors\":\"W. Villegas-Ch., Ángel Jaramillo-Alcázar, Sergio Luján-Mora\",\"doi\":\"10.3390/bdcc8010008\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study evaluated the generation of adversarial examples and the subsequent robustness of an image classification model. The attacks were performed using the Fast Gradient Sign method, the Projected Gradient Descent method, and the Carlini and Wagner attack to perturb the original images and analyze their impact on the model’s classification accuracy. Additionally, image manipulation techniques were investigated as defensive measures against adversarial attacks. The results highlighted the model’s vulnerability to conflicting examples: the Fast Gradient Signed Method effectively altered the original classifications, while the Carlini and Wagner method proved less effective. Promising approaches such as noise reduction, image compression, and Gaussian blurring were presented as effective countermeasures. These findings underscore the importance of addressing the vulnerability of machine learning models and the need to develop robust defenses against adversarial examples. This article emphasizes the urgency of addressing the threat posed by harmful standards in machine learning models, highlighting the relevance of implementing effective countermeasures and image manipulation techniques to mitigate the effects of adversarial attacks. These efforts are crucial to safeguarding model integrity and trust in an environment marked by constantly evolving hostile threats. An average 25% decrease in accuracy was observed for the VGG16 model when exposed to the Fast Gradient Signed Method and Projected Gradient Descent attacks, and an even more significant 35% decrease with the Carlini and Wagner method.\",\"PeriodicalId\":505155,\"journal\":{\"name\":\"Big Data and Cognitive Computing\",\"volume\":\" 15\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-01-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Big Data and Cognitive Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/bdcc8010008\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Big Data and Cognitive Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/bdcc8010008","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

本研究评估了对抗性示例的生成以及图像分类模型随后的鲁棒性。使用快速梯度符号法、投影梯度下降法以及 Carlini 和 Wagner 攻击法对原始图像进行扰动,并分析其对模型分类准确性的影响。此外,还研究了图像处理技术,作为抵御对抗性攻击的防御措施。结果凸显了该模型在冲突实例面前的脆弱性:快速梯度符号法有效地改变了原始分类,而卡利尼和瓦格纳法的效果较差。降噪、图像压缩和高斯模糊等有前途的方法被认为是有效的对策。这些发现强调了解决机器学习模型脆弱性问题的重要性,以及开发针对对抗性示例的强大防御措施的必要性。本文强调了解决机器学习模型中有害标准所带来的威胁的紧迫性,突出了实施有效的应对措施和图像处理技术以减轻对抗性攻击影响的相关性。在敌意威胁不断演变的环境中,这些努力对于保障模型的完整性和信任度至关重要。在受到快速梯度符号法和投射梯度下降法攻击时,VGG16 模型的准确率平均下降了 25%,而在受到 Carlini 和 Wagner 方法攻击时,准确率更是显著下降了 35%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Evaluating the Robustness of Deep Learning Models against Adversarial Attacks: An Analysis with FGSM, PGD and CW
This study evaluated the generation of adversarial examples and the subsequent robustness of an image classification model. The attacks were performed using the Fast Gradient Sign method, the Projected Gradient Descent method, and the Carlini and Wagner attack to perturb the original images and analyze their impact on the model’s classification accuracy. Additionally, image manipulation techniques were investigated as defensive measures against adversarial attacks. The results highlighted the model’s vulnerability to conflicting examples: the Fast Gradient Signed Method effectively altered the original classifications, while the Carlini and Wagner method proved less effective. Promising approaches such as noise reduction, image compression, and Gaussian blurring were presented as effective countermeasures. These findings underscore the importance of addressing the vulnerability of machine learning models and the need to develop robust defenses against adversarial examples. This article emphasizes the urgency of addressing the threat posed by harmful standards in machine learning models, highlighting the relevance of implementing effective countermeasures and image manipulation techniques to mitigate the effects of adversarial attacks. These efforts are crucial to safeguarding model integrity and trust in an environment marked by constantly evolving hostile threats. An average 25% decrease in accuracy was observed for the VGG16 model when exposed to the Fast Gradient Signed Method and Projected Gradient Descent attacks, and an even more significant 35% decrease with the Carlini and Wagner method.
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
期刊最新文献
Breast Cancer Detection and Localizing the Mass Area Using Deep Learning Trends and Challenges Towards Effective Data-Driven Decision Making in UK Small and Medium-Sized Enterprises: Case Studies and Lessons Learnt from the Analysis of 85 Small and Medium-Sized Enterprises Demystifying Mental Health by Decoding Facial Action Unit Sequences AMIKOMNET: Novel Structure for a Deep Learning Model to Enhance COVID-19 Classification Task Performance The State of the Art of Artificial Intelligence Applications in Eosinophilic Esophagitis: A Systematic Review
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1