面向对抗样本攻击的移动目标防御

王滨; 陈靓; 钱亚冠; 郭艳凯; 邵琦琦; 王佳敏

doi:10.11959/j.issn.2096-109x.2021012

您当前的位置：

首页 >

文章列表页 >

面向对抗样本攻击的移动目标防御

学术论文 | 更新时间：2024-06-03

- 面向对抗样本攻击的移动目标防御
- Moving target defense against adversarial attacks
- 网络与信息安全学报 2021年7卷第1期页码：113-120
- 作者机构：
  
  1. 浙江科技学院大数据学院，浙江杭州 310023
  2. 浙江大学电气工程学院，浙江杭州 310058
  3. 海康威视数字技术有限公司网络与信息安全实验室，浙江杭州 310058
- 作者简介：
  
  [ "王滨（1978- ），男，山东泗水人，海康威视数字技术有限公司研究员，主要研究方向为人工智能安全、物联网安全、密码学等。" ]
  [ "陈靓（1995- ），男，江苏无锡人，浙江科技学院硕士生，主要研究方向为对抗深度学习、神经网络压缩。" ]
  [ "钱亚冠（1976- ），男，浙江嵊州人，博士，浙江科技学院副教授，主要研究方向为人工智能安全、机器学习与大数据处理、对抗性机器学习。" ]
  [ "郭艳凯（1994- ），男，河南驻马店人，浙江科技学院硕士生，主要研究方向为深度学习图像处理、对抗深度学习。" ]
  [ "邵琦琦（1997- ），女，浙江永嘉人，浙江科技学院硕士生，主要研究方向为深度学习安全。" ]
  [ "王佳敏（1993- ），女，浙江新沂人，浙江科技学院硕士生，主要研究方向为深度学习安全。" ]
- 基金信息：
  
  2019年度杭州市领军型创新团队项目;Science and Technology Project of State Grid Corporation of China;国家重点研发计划;TheNational Key R＆D Program of China(2018YFB2100400);国家电网公司总部科技项目;Hangzhou City Leading Innovation Team Project in 2019(5700-202019187A-0-0-00)
- DOI：10.11959/j.issn.2096-109x.2021012
  中图分类号： TP393
- 网络首发：2021-02，
  
  纸质出版：2021-02-15
- 稿件说明：
移动端阅览
王滨, 陈靓, 钱亚冠, 等. 面向对抗样本攻击的移动目标防御[J]. 网络与信息安全学报, 2021,7(1):113-120.

Bin WANG, Liang CHEN, Yaguan QIAN, et al. Moving target defense against adversarial attacks[J]. Chinese Journal of Network and Information Security, 2021, 7(1): 113-120.
王滨, 陈靓, 钱亚冠, 等. 面向对抗样本攻击的移动目标防御[J]. 网络与信息安全学报, 2021,7(1):113-120. DOI： 10.11959/j.issn.2096-109x.2021012.

Bin WANG, Liang CHEN, Yaguan QIAN, et al. Moving target defense against adversarial attacks[J]. Chinese Journal of Network and Information Security, 2021, 7(1): 113-120. DOI： 10.11959/j.issn.2096-109x.2021012.

摘要

深度神经网络已被成功应用于图像分类，但研究表明深度神经网络容易受到对抗样本的攻击。提出一种移动目标防御方法，通过 Bayes-Stackelberg 博弈策略动态切换模型，使攻击者无法持续获得一致信息，从而阻断其构建对抗样本。成员模型的差异性是提高移动目标防御效果的关键，将成员模型之间的梯度一致性作为度量，构建新的损失函数进行训练，可有效提高成员模型之间的差异性。实验结果表明，所提出的方法能够提高图像分类系统的移动目标防御性能，显著降低对抗样本的攻击成功率。

Abstract

Deep neural network has been successfully applied to image classification

but recent research work shows that deep neural network is vulnerable to adversarial attacks.A moving target defense method was proposed by means of dynamic switching model with a Bayes-Stackelberg game strategy

which could prevent an attacker from continuously obtaining consistent information and thus blocked its construction of adversarial examples.To improve the defense effect of the proposed method

the gradient consistency among the member models was taken as a measure to construct a new loss function in training for improving the difference among the member models.Experimental results show that the proposed method can improve the moving target defense performance of the image classification system and significantly reduce the attack success rate against the adversarial examples.

关键词

Keywords

references

HOLI G , JAIN D K . Convolutional neural network approach for extraction and recognition of digits from bank cheque images [M ] // Emerging Research in Electronics,Computer Science and Technology . 2019 : 331 - 341 .

FOMIN I S , BAKHSHIEV A V . Research on convolutional neural network for object classification in outdoor video surveillance system [C ] // International Conference on Neuroinformatics . 2019 : 221 - 229 .

BUYVAL A , GABDULLIN A , LYUBIMOV M . Road sign detection and localization based on camera and lidar data [C ] // Eleventh International Conference on Machine Vision (ICMV 2018) . 2019 :1104125.

SZEGEDY C , ZAREMBA W , SUTSKEVER I , et al . Intriguing properties of neural networks [J ] . arXiv preprint arXiv:1312.6199 , 2013 .

GOODFELLOW I J , SHLENS J , SZEGEDY C . Explaining and harnessing adversarial examples [J ] . arXiv preprint arXiv:1412.6572 , 2014 .

MADRY A , MAKELOV A , SCHMIDT L , et al . Towards deep learning models resistant to adversarial attacks [J ] . arXiv preprint arXiv:1706.06083 , 2017 .

SENGUPTA S , CHAKRABORTI T , KAMBHAMPATI S . MTDeep:moving target defense to boost the security of deep neural nets against adversarial attacks [M ] . Proc GameSec , 2019 .

ZHUANG R , DELOACH S A , OU X . Towards a theory of moving target defense [C ] // Proceedings of the First ACM Workshop on Moving Target Defense . 2014 : 31 - 40 .

RUSSAKOVSKY O , DENG J , SU H , et al . ImageNet large scale visual recognition challenge [J ] . International Journal of Computer Vision , 2015 , 115 ( 3 ): 211 - 252 .

DONG Y , LIAO F , PANG T , et al . Boosting adversarial attacks with momentum [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2018 : 9185 - 9193 .

XIE C , ZHANG Z , ZHOU Y , et al . Improving transferability of adversarial examples with input diversity [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2019 : 2730 - 2739 .

PARUCHURI P , PEARCE J P , TAMBE M , et al . An efficient heuristic approach for security against multiple adversaries [C ] // In AAMAS . 2007 .

PARUCHURI P , PEARCE J P , MARECKI J , et al . Playing games for security:an efficient exact algorithm for solving Bayesian-Stackelberg games [C ] // Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems- Volume 2 . 2008 : 895 - 902 .

DENG J , DONG W , SOCHER R , et al . ImageNet:a large-scale hierarchical image database [C ] // IEEE Conference on Computer Vision ＆ Pattern Recognition . IEEE , 2009 .

SZEGEDY C , LIU W , JIA Y , et al . Going deeper with convolutions [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2015 : 1 - 9 .

SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [J ] . arXiv preprint arXiv:1409.1556 , 2014 .

HE K , ZHANG X , REN S , et al . Deep residual learning for image recognition [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2016 : 770 - 778 .

浏览量

682

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向网络层的动态跳变技术研究进展

容器云中基于Stackelberg博弈的动态异构调度方法

深度学习中的对抗攻击与防御

敌对攻击环境下基于移动目标防御的算法稳健性增强方法

面向SDN的移动目标防御技术研究进展