基于RSA的图像可识别对抗攻击方法

doi:10.11959/j.issn.2096-109x.2021065

Abstract

Abstract:

Adversarial attack is an important part of deep learning security research.Relying on the RSA signature schemes and RSA encryption schemes in cryptography, an adversarial attack method that adversarial examples can be recognized by a specific classifier is proposed.Through the idea of one pixel attack, the normal image can have the ability to make other classifier misclassify while embedding additional information.It can be used in classifier authorization management, online image anti-counterfeiting, etc.The experiment show that the adversarial examples can be recognized under the specific classifier, and the disturbance noise is difficult to detect by the human eye.

Key words: adversarial attack, signature scheme, encryption scheme, cryptography, classifier, image recognition

CLC Number:

TP181

Yu ZHANG, Hailiang LI. RSA-based image recognizable adversarial attack method[J]. Chinese Journal of Network and Information Security, 2021, 7(5): 40-48.

Figures/Tables 10

References 29

[1]	LE-CUN Y , BENGIO Y , HINTON G . Deep learning[J]. Nature, 2015,521(7553): 436-444.
[2]	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.
[3]	GUO G , ZHANG N . A survey on deep learning based face recognition[J]. Computer Vision and Image Understanding, 2019,189:102805.
[4]	DENG L , HINTON G , KINGSBURY B . New types of deep neural network learning for speech recognition and related applications:an overview[C]// 2013 IEEE International Conference on Acoustics,Speech and Signal Processing. 2013: 8599-8603.
[5]	YOUNG T , HAZARIKA D , PORIA S ,et al. Recent trends in deep learning based natural language processing[J]. IEEE Computational Intelligence Magazine, 2018,13(3): 55-75.
[6]	GOODFELLOW I J , SHLENS J , SZEGEDY C . Explaining and harnessing adversarial examples[J]. arXiv preprint arXiv:1412.6572, 2014.
[7]	DENG J , DONG W , SOCHER R ,et al. Imagenet:a large-scale hierarchical image database[C]// 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009: 248-255.
[8]	何英哲, 胡兴波, 何锦雯 ,等. 机器学习系统的隐私和安全问题综述[J]. 计算机研究与发展, 2019,56(10): 2049.
	HE Y Z , HU X B , HE J W ,et al. Overview of the privacy and security issues of machine learning systems[J]. Computer Research and Development, 2019,56(10): 2049.
[9]	ZHENG T , CHEN C , REN K . Distributionally adversarial attack[C]// Proceedings of the AAAI Conference on Artificial Intelligence. 2019: 2253-2260.
[10]	XIAO C , LI B , ZHU J Y ,et al. Generating adversarial examples with adversarial networks[J]. arXiv preprint arXiv:1801.02610, 2018.
[11]	QIU S , LIU Q , ZHOU S ,et al. Review of artificial intelligence adversarial attack and defense technologies[J]. Applied Sciences, 2019,9(5): 909.
[12]	AKHTAR N , MIAN A . Threat of adversarial attacks on deep learning in computer vision:a survey[J]. IEEE Access, 2018,6: 14410-14430.
[13]	KURAKIN A , GOODFELLOW I , BENGIO S ,et al. Adversarial attacks and defences competition[M]// The NIPS'17 Competition:Building Intelligent Systems. 2018: 195-231.
[14]	TRAMèR F , KURAKIN A , PAPERNOT N ,et al. Ensemble adversarial training:attacks and defenses[J]. arXiv preprint arXiv:1705.07204, 2017.
[15]	MADRY A , MAKELOV A , SCHMIDT L ,et al. Towards deep learning models resistant to adversarial attacks[J]. arXiv preprint arXiv:1706.06083, 2017.
[16]	LIANG B , LI H , SU M ,et al. Detecting adversarial image examples in deep neural networks with adaptive noise reduction[J]. IEEE Transactions on Dependable and Secure Computing, 2018: 1-10.
[17]	PAPERNOT N , MCDANIEL P , WU X ,et al. Distillation as a defense to adversarial perturbations against deep neural networks[C]// 2016 IEEE Symposium on Security and Privacy (SP). 2016: 582-597.
[18]	JIA X , WEI X , CAO X ,et al. Comdefend:an efficient image compression model to defend adversarial examples[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 6084-6092.
[19]	SZEGEDY C , ZAREMBA W , SUTSKEVER I ,et al. Intriguing properties of neural networks[J]. arXiv preprint arXiv:1312.6199, 2013.
[20]	张思思, 左信, 刘建伟 . 深度学习中的对抗样本问题[J]. 计算机学报, 2019,42(8): 1886-1904.
	ZHANG S S , ZUO X , LIU J W . The problem of adversarial examples in deep learning[J]. Chinese Journal of Computers, 2019,42(8): 1886-1904.
[21]	段广晗, 马春光, 宋蕾 ,等. 深度学习中对抗样本的构造及防御研究[J]. 网络与信息安全学报, 2020,6(2): 1-11.
	DUAN G H , MA C G , SONG L ,et al. Research on structure and defense of adversarial example in deep learning[J]. Chinese Journal of Network and Information Security, 2020,6(2): 1-11.
[22]	刘西蒙, 谢乐辉, 王耀鹏 ,等. 深度学习中的对抗攻击与防御[J]. 网络与信息安全学报, 2020,6(5): 36-53.
	LIU X M , XIE L H , WANG Y P ,et al. Adversarial attacks and defenses in deep learning[J]. Chinese Journal of Network and Information Security, 2020,6(5): 36-53.
[23]	薛锐 . 公钥加密理论[M]. 北京: 科学出版社, 2016.
	XUE R . Public key encryption theory[M]. Beijing: Science Press, 2016.
[24]	DIFFIE W , HELLMAN M . New directions in cryptography[J]. IEEE Transactions on Information Theory, 1976,22(6): 644-654.
[25]	RIVEST R L , SHAMIR A , ADLEMAN L . A method for obtaining digital signatures and public-key cryptosystems[J]. Communications of the ACM, 1978,21(2): 120-126.
[26]	DONG Y , FU Q A , YANG X ,et al. Benchmarking adversarial robustness on image classification[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 321-331.
[27]	MADRY A , MAKELOV A , SCHMIDT L ,et al. Towards deep learning models resistant to adversarial attacks[J]. arXiv preprint arXiv:1706.06083, 2017.
[28]	HYUN K , KIM Y , PARK K W ,et al. Friend-safe evasion attack:an adversarial example that is correctly recognized by a friendly classifier[J]. Computers ＆ Security, 2018,78: 380-397.
[29]	SU J , VARGAS D V , SAKURAI K . One pixel attack for fooling deep neural networks[J]. IEEE Transactions on Evolutionary Computation, 2019,23(5): 828-841.

Metrics

Recommended 0

No Suggested Reading articles found!

迭代次数	攻击成功数	攻击成功率
0	370	37%
5	707	70.7%
10	771	77.1%
15	799	79.9%
20	808	80.8%

对抗攻击	噪声	可特定识别性
本文方法	408～448 bit	√
单像素攻击	1bit	×
快速梯度下降攻击	全局像素	×
Deepfool攻击	全局像素	×
C＆W攻击	全局像素	×

RSA-based image recognizable adversarial attack method

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 29

Related Articles 15

Metrics

Recommended 0

[1]	Xianyi CHEN, Jun GU, Kai YAN, Dong JIANG, Linfeng XU, Zhangjie FU. Double adversarial attack against license plate recognition system [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 16-27.
[2]	Ruiqi XIA, Manman LI, Shaozhen CHEN. Identification on the structures of block ciphers using machine learning [J]. Chinese Journal of Network and Information Security, 2023, 9(3): 79-89.
[3]	Jinyin CHEN, Rongchang LI, Guohan HUANG, Tao LIU, Haibin ZHENG, Yao CHENG. Survey on vertical federated learning: algorithm, privacy and security [J]. Chinese Journal of Network and Information Security, 2023, 9(2): 1-20.
[4]	Yitian GAO, Liquan CHEN, Tianyang TU, Yuan GAO, Qianye CHEN. Post-quantum encryption technology based on BRLWE for internet of things [J]. Chinese Journal of Network and Information Security, 2022, 8(5): 140-149.
[5]	Feng LIU, Jie YANG, Jiayin QI. Survey on blockchain privacy protection techniques in cryptography [J]. Chinese Journal of Network and Information Security, 2022, 8(4): 29-44.
[6]	Dian LIN, Li PAN, Ping YI. Research on the robustness of convolutional neural networks in image recognition [J]. Chinese Journal of Network and Information Security, 2022, 8(3): 111-122.
[7]	Jianlin NIU, Zhiyu REN, Xuehui DU. Cross-domain authentication scheme based on consortium blockchain [J]. Chinese Journal of Network and Information Security, 2022, 8(3): 123-133.
[8]	Yongcheng SONG, Xinyi HUANG, Wei WU, Haixia CHEN. Survey of code-based digital signatures [J]. Chinese Journal of Network and Information Security, 2021, 7(4): 1-17.
[9]	Jinyin CHEN, Dunjie ZHANG, Guohan HUANG, Xiang LIN, Liang BAO. Adversarial attack and defense on graph neural networks: a survey [J]. Chinese Journal of Network and Information Security, 2021, 7(3): 1-28.
[10]	Zhen ZHOU, Debiao HE, Min LUO, Li LI. Compact software/hardware co-design and implementation method of Aigis-sig digital signature scheme [J]. Chinese Journal of Network and Information Security, 2021, 7(2): 64-76.
[11]	Ximeng LIU,Lehui XIE,Yaopeng WANG,Xuru LI. Adversarial attacks and defenses in deep learning [J]. Chinese Journal of Network and Information Security, 2020, 6(5): 36-53.
[12]	Shaozhuo LI,Na WANG,Xuehui DU. Privacy protection mechanism of on-demand disclosure on blockchain [J]. Chinese Journal of Network and Information Security, 2020, 6(3): 19-29.
[13]	ZHANG Ning,TAN Shichong,FU Xiaotong,DU Xiaogang,LI Hui. Summary and study on the curriculum reform of modern cryptography based on SPOC and flip classroom [J]. Chinese Journal of Network and Information Security, 2019, 5(3): 89-95.
[14]	WU Wanqing,DU Ruizhong. Evaluation of blended instruction based on network platform in cryptography teaching [J]. Chinese Journal of Network and Information Security, 2019, 5(3): 96-101.
[15]	Zhong WANG,Yiliang HAN. Simple Matrix encryption scheme with variable ciphertext length [J]. Chinese Journal of Network and Information Security, 2018, 4(4): 56-62.