吉林大学学报(工学版) ›› 2021, Vol. 51 ›› Issue (3): 1060-1066.doi: 10.13229/j.cnki.jdxbgxb20200521

• 计算机科学与技术 • 上一篇    

基于循环生成对抗网络的学习型光学图像加密方案

李锦青1,2(),周健1,2,底晓强1,2,3   

  1. 1.长春理工大学 计算机科学技术学院，长春 130022
    2.长春理工大学 吉林省网络与信息安全重点实验室，长春 130022
    3.长春理工大学 信息化中心，长春 130022
  • 收稿日期:2020-07-11 出版日期:2021-05-01 发布日期:2021-05-07
  • 作者简介:李锦青(1980-),女,副教授,博士.研究方向:信息安全,网络安全,图像加密. E-mail:lijinqing@cust.edu.cn
  • 基金资助:
    国家重点研发计划项目(2018YFB1800303);吉林省自然科学基金项目(20190201188JC);吉林省高等教育教学改革研究项目(JLLG685520190725093004)

Learning optical image encryption scheme based on CycleGAN

Jin-qing LI1,2(),Jian ZHOU1,2,Xiao-qiang DI1,2,3   

  1. 1.School of Computer Science and Technology，Changchun University of Science and Technology，Changchun 130022，China
    2.Jilin Province Key Laboratory of Network and Information Security，Changchun University of Science and Technology，Changchun 130022，China
    3.Information Center，Changchun University of Science and Technology，Changchun 130022，China
  • Received:2020-07-11 Online:2021-05-01 Published:2021-05-07

RICH HTML

 5   

PDF (PC)

410

摘要：

为克服光学图像加密方法受光学器件性能限制和随机相位掩膜板制造工艺复杂的问题，提出了一种基于循环生成对抗网络（CycleGAN）的学习型光学图像加密方案。首先，使用经典双随机相位编码加密明文样本图像，构造出明文图像-密文图像训练集。然后，将其作为循环生成对抗网络的输入，自动学习光学图像加密的加密特性，训练得到光学图像加密学习模型。最后，利用仿真实验对使用CycleGAN训练的加密模型生成的图像进行加密解密性能测试。数据分析表明，该模型能够有效保护图像信息的安全和较好地恢复密文图像，学习型光学加密模型具有加密性能不受光学加密器件限制的优点，可以实现批量图像的快速加密。

关键词: 图像安全性, 循环生成对抗网络, 深度学习, 光学图像加密, 双随机相位编码

Abstract:

To overcome the problem that the effect of optical image encryption is limited by the processing technology of the optical encryption devices and the manufacturing process of the random phase mask is complicated， in this paper， an optical image encryption learning scheme based on cycle-consistent adversarial networks （CycleGAN） is proposed. Firstly， the classic double random phase encoding is used to encrypt the plain image to generate a plain-cipher training set. Secondly， the training set is input to CycleGAN to automatically learn the encryption characteristics of optical image encryption to obtain an optical image encryption learning model. Finally， encryption and decryption performance tests are carried out by simulation experiments on the images generated by the learning encryption mechanism of CycleGAN. Data analysis shows that this scheme can effectively protect the security of image information and recover ciphertext images well. In addition， the encryption performance is not limited by optical encryption equipment， which can realize the rapid encryption of batches of images.

Key words: image security, cycle-consistent adversarial networks, deep learning, optical image encryption, double random phase encoding

中图分类号: 

  • TP391

图1

双随机相位编码的工作流程"

图2

循环生成对抗网络示意图"

图3

基于CycleGAN的光学图像加密解密方案"

图4

实验结果"

图5

直方图分析"

图6

相关性分析"

表1

密文图像相关性分析"

图像水平相关性垂直相关性对角相关性
图4(a1)0.08770.13790.0349
图4(a2)0.15450.10020.0261
图4(a3)0.12960.12490.0483
图4(a4)0.13570.15250.0074

图7

密文图像和明文图像的峰值信噪比"

图8

解密效果分析似性"

表2

加密/解密速度分析"

图像数量图像大小加密时间/s解密时间/s
100256×2564.38934.3905
1000256×25616.841916.7958
1 Refregier P, Javidi B. Optical image encryption based on input plane and Fourier plane random encoding[J]. Optics Letters, 1995, 20(7):767-769.
2 陈晓冬, 底晓强, 李锦青. 基于多混沌和分数Fourier的光学图像加密算法[J]. 南京大学学报:自然科学, 2019, 55(2):251-263.
Chen Xiao-dong, Di Xiao-qiang, Li Jin-qing, et al. Optical image encryption algorithm based on multi chaos and fractional fourier[J]. Journal of Nanjing University(Natural Sciences), 2019, 55(2):251-263.
3 Ben F M A, Guesmi R, Kachouri A, et al. A novel chaos based optical image encryption using fractional Fourier transform and DNA sequence operation[J]. Optics And Laser Technology, 2020, 121:No.105777.
4 Kong D, Shen X. Multiple-image encryption based on optical wavelet transform and multichannel fractional Fourier transform[J]. Optics And Laser Technology, 2014, 57(4):343-349.
5 Wang M M, Pousset Y, Carré P, et al. Optical image encryption scheme based on apertured fractional Mellin transform[J]. Optics and Laser Technology, 2020, 124:No.106001.
6 Luan G Y, Li A C, Chen Z G, et al. Asymmetric optical image encryption with silhouette removal using interference and equal modulus decomposition[J]. IEEE Photonics Journal, 2020, 12(2):No.2963921.
7 Chen W, Javidi B, Chen X. Advances in optical security systems[J]. Advances in Optics and Photonics, 2014, 6(2):120-155.
8 Chen J, Li X W, Wang Q H. Deep learning for improving the robustness of image encryption[J]. IEEE Access, 2019, 7:181083-181091.
9 Pan S, Wei J G, Hu S B. A aovel image encryption algorithm based on hybrid chaotic mapping and intelligent learning in financial security system[J]. Multimedia Tools and Applications, 2020, 79(13/14):9163-9176.
10 程婉琪. 图像加密光学实现方法研究[D]. 重庆:重庆大学通信工程学院, 2017.
Chen Wan-qi. Research on optical implementation of image encryption[D]. Chongqing:College of Communication Engineering, Chongqing University, 2017.
11 Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J/OL]. [2020-06-30].
12 Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]∥Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 2017:2223-2232.
13 Di Xiao-qiang, Li Jin-qing, Hui Qi, et al. A semi-symmetric image encryption scheme based on the function projective synchronization of two hyperchaotic systems[J]. Plos One, 2017, 12(9):No.0184586.
14 Man Zhen-long, Li Jin-qiang, Di Xiao-qiang, et al. An image segmentation encryption algorithm based on hybrid chaotic system[J]. IEEE Access, 2019,7:103047-103058.
15 底晓强, 王英政, 李锦青, 等. 基于量子细胞神经网络超混沌的视频加密方法[J]. 吉林大学学报:工学版, 2018, 48(3):919-928.
Di Xiao-qiang, Wang Ying-zheng, Li Jin-qing, et al. Video encryption method based on hyperchaos of quantum cellular neural networks[J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(3):919-928.
16 Liu Y L, Qu X X, Xin G J. A ROI-based reversible data hiding scheme in encrypted medical images[J]. Journal of Visual Communication and Image Representation, 2016, 39:51-57.
[1] 赵宏伟,刘晓涵,张媛,范丽丽,龙曼丽,臧雪柏. 基于关键点注意力和通道注意力的服装分类算法[J]. 吉林大学学报(工学版), 2020, 50(5): 1765-1770.
[2] 谌华,郭伟,闫敬文,卓文浩,吴良斌. 基于深度学习的SAR图像道路识别新方法[J]. 吉林大学学报(工学版), 2020, 50(5): 1778-1787.
[3] 郜峰利,陶敏,李雪妍,何昕,杨帆,王卓,宋俊峰,佟丹. 基于深度学习的CT影像脑卒中精准分割[J]. 吉林大学学报(工学版), 2020, 50(2): 678-684.
[4] 徐谦,李颖,王刚. 基于深度学习的行人和车辆检测[J]. 吉林大学学报(工学版), 2019, 49(5): 1661-1667.
[5] 郭立民,陈鑫,陈涛. 基于AlexNet模型的雷达信号调制类型识别[J]. 吉林大学学报(工学版), 2019, 49(3): 1000-1008.
[6] 李抵非, 田地, 胡雄伟. 基于分布式内存计算的深度学习方法[J]. 吉林大学学报(工学版), 2015, 45(3): 921-925.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发