Moving target defense against adversarial attacks

Bin WANG; Liang CHEN; Yaguan QIAN; Yankai GUO; Qiqi SHAO; Jiamin WANG

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

您当前的位置：

首页 >

文章列表页 >

Moving target defense against adversarial attacks

Papers | 更新时间：2024-06-03

- Moving target defense against adversarial attacks
- Chinese Journal of Network and Information Security Vol. 7, Issue 1, Pages: 113-120(2021)
- 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：
- 基金信息：
- DOI：10.11959/j.issn.2096-109x.2021012
  CLC： TP393
- Online First：2021-02，
  
  Published：15 February 2021
- 稿件说明：
移动端阅览
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：

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 .

Views

682

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research progress on dynamic hopping technology for network layer

Dynamic heterogeneous scheduling method based on Stackelberg game model in container cloud

Adversarial attacks and defenses in deep learning

Improve the robustness of algorithm under adversarial environment by moving target defense

Research progress on moving target defense for SDN

Related Author

Guozhen CHENG

Shumin HUO

Jinglei TAN

Jie NIU

Fucai CHEN

Weizhen HE

Shumin HUO

Lingshu LI

Related Institution

Information Engineering University

Unit 61212 of the Chinese People's Liberation Army

College of Mathematics and Computer Science,Fuzhou University

Guangdong Provincial Key Laboratory of Data Security and Privacy Protection

School of Computer Science and Technology,East China Normal University

⁰