相較於傳統以整張圖像進行加密的方式，對圖像上少數重點區域進行加密的方式具有較好的加密效率及計算時所耗費的空間較少等優點。且近年來圖像處理因其對圖像中物體的檢測和分類精度高而受到廣泛關注。因此，本論文在加密演算法的基礎上，加上深度學習來建構一個以二維超渾沌系統用於感興趣區域圖像加密之演算法，並探究其安全性。

首先，本論文設計了一個新穎的二維超渾沌系統，接著以軌跡圖、分歧圖、蛛網圖、李亞普諾夫指數及NIST測試對渾沌系統進行驗證，發現其展現了更大的渾沌範圍及更好的不可預測性。並首次使用了名為八卦編碼的編碼架構。我們將以上兩點論述結合，可增強明文圖像於排列過程之效果，從而增加我們加密的複雜性。而此加密演算法還利用了明文圖像上的特徵提取和安全雜湊演算法256位元以生成密鑰，再搭配上進階互斥或運算及位元位移運算步驟，完成對明文圖像的加密。

再來我們導入了YoloV3 與 UNet用以物件辨識及選取。使用者可以針對圖像上的感興趣區域實行自動選取，接著將所選取的部分不規則區域，利用加密演算法進行加密，以完成區域加密的動作。而對於不同的傳輸者及接收者而言，每張圖像的加密區域不盡相同，故我們稱之為感興趣區域加密。

最後，我們對密文圖像進行安全性分析用以驗證加密系統之安全性。包括密鑰分析、選擇性明文及選擇性密文分析、直方圖分析、相關性分析、抵抗差分攻擊分析、夏儂熵分析及穩健性分析等，由結果可知我們通過了所有測試，擁有足夠的安全性。接著我們對本論文所描述加密演算法之內容提出未來改進方向及建議。

Variable area image encryption shows several advantages over traditional image encryption methods. For example, it has less computational effort and less memory usage since it encrypts only a fraction of the entire image. In recent years, image processing has attracted a lot of attention due to its high accuracy to detect and classify objects in images. Therefore, based on the encryption algorithm, this thesis adds deep learning to construct an algorithm that uses a hyper chaotic system for image encryption and explores its security.

First, we design a novel two-dimensional hyper chaotic map, and then verifies the characteristics of the chaotic map with trajectory diagram, bifurcation diagram, cobweb plot, Lyapunov exponent and NIST test, finds that it has a greater range of chaos and better unpredictability. And for the first time we use a coding architecture called Bagua coding. We combine the above two points to enhance the effect of the permutation process, and consequently, the complexity of our encryption scheme. The algorithm also uses the features extraction on the plaintext and SHA-256 to generate secret key, coupled with the advanced exclusive-or operation and bit shift calculation to encrypt the plaintext.

Next, we import YoloV3 and UNet for object detection and selection. User can automatically select region of interest on the image and use encryption algorithm to encrypt the selected part of irregular region. For different transmitters and receivers, encryption area of each image is not the same, so we call it region of interest encryption.

Finally, we perform security analysis on ciphertext image. The security analysis results on the generated ciphertext image validate our proposed encryption framework against statistical and differential attacks. Then we propose the future improvement direction for the content of encryption algorithm in this thesis.

[1] G. Alvarez, S. Li, “Some basic cryptographic requirements for chaos-based cryptosystem,” International Journal of Bifurcation and chaos, vol. 16, no. 8, pp. 656–715, Aug. 2006.
[2] C. E. Shannon, “Communication theory of secrecy systems,” Bell System Technical Journal, vol. 28, no. 4, pp. 656–715, Oct. 1949.
[3] A. S. Wightman, “Problèmes Ergodiques de la Mécanique Classique. VI Arnold and A. Avez. Gauthier-Villars, Paris, 1967. iv+ 243 pp., illus. Paper, 48 F. Monographies Internationales de Mathématiques Modernes,” American Association for the Advancement of Science, vol. 159, no. 3821, pp. 1344, Mar. 1968.
[4] R. Matthews, “On the derivation of a “chaotic” encryption algorithm,” Cryptologia, vol. 13, no. 1, pp. 29–42, 1989.
[5] T. Yang, C. W. Wu, L. O. Chua, "Cryptography based on chaotic systems, " IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, vol. 44, no. 5, pp. 469–472, May. 1997.
[6] J. Fridrich, “Symmetric ciphers based on two-dimensional chaotic maps,” International Journal of Bifurcation and chaos, vol. 8, no. 6, pp. 1259–1284, Jun. 1998.
[7] G. Chen, Y. Mao, C. K. Chui, “A symmetric image encryption scheme based on 3D chaotic cat maps,” Chaos, Solitons & Fractals, vol. 21, no. 3, pp. 746–761, Jul. 2004.
[8] N. K. Pareek, V. Patidar, K. K. Sud, “Image encryption using chaotic logistic map,” Image and vision computing, vol. 24, no. 9, pp. 926–934, Sep. 2006.
[9] X. Wang, L. Teng, X. Qin, “A novel colour image encryption algorithm based on chaos,” Signal Processing, vol. 92, no. 4, pp. 1101–1108, Apr. 2012.
[10] Y. Zhou, L. Bao, C. L. P. Chen, “A new 1D chaotic system for image encryption,” Signal processing, vol. 97, pp. 172–182, Apr. 2014.
[11] Z. Hua, Y. Zhou, C. M. Pun, C. L. P. Chen, “2D Sine Logistic modulation map for image encryption,” Information Sciences, vol. 297, pp. 80–94, Aar. 2015.
[12] H. Zhu, Y. Zhao, Y. Song, “2D logistic-modulated-sine-coupling-logistic chaotic map for image encryption,” IEEE Access, vol. 7, pp. 14081–14098, 2019.
[13] L. M. Adleman, “Molecular computation of solutions to combinatorial problems,” Science, vol. 266, no. 5187, pp. 1021–1024, Nov. 1994.
[14] X. Zheng, J. Xu, W. Li, “Parallel DNA arithmetic operation based on n-moduli set,” Applied Mathematics and Computation, vol. 212, no. 1, pp. 177–184, Jun. 2009.
[15] H. Liu, X. Wang, A. Kadir, “Image encryption using DNA complementary rule and chaotic maps,” Applied Soft Computing, vol. 12, no. 5, pp. 1457–1466, May. 2012.
[16] J. Wu, X. Liao, B. Yang, “Image encryption using 2D Hénon-Sine map and DNA approach,” Signal Processing, vol. 153, pp. 11–23, Dec. 2018.
[17] Y. Q. Zhang, X. Y. Wang, J. Liu, Z. L. Chi, “An image encryption scheme based on the MLNCML system using DNA sequences,” Optics and Lasers in Engineering, vol. 82, pp. 95–103, Jun. 2016.
[18] X. Y. Wang, H. L. Zhang, X. M. Bao, “Color image encryption scheme using CML and DNA sequence operations,” Biosystems, vol. 144, pp. 16–28, Jun. 2016.
[19] J. Chen, Z. L. Zhu, L. B. Zhang, Y. Zhang, B. Q. Yang, “Exploiting self-adaptive permutation-diffusion and DNA random encoding for secure and efficient image encryption,” Signal Processing, vol. 142, pp. 340–353, Jan. 2018.
[20] L. Liu, D. Wang, Y. Lei, “An image encryption scheme based on hyper chaotic system and DNA with fixed secret keys,” IEEE Access, vol. 8, pp. 46400–46416, 2020.
[21] D. Xiao, Q. Fu, T. Xiang, Y. Zhang, “Chaotic image encryption of regions of interest,” International Journal of Bifurcation and Chaos, vol. 26, no. 11, Oct. 2016.
[22] H. W. Xue, J. Du, S. L. Li, W. J. Ma, “Region of interest encryption for color images based on a hyperchaotic system with three positive Lyapunov exponets,” Optics & Laser Technology, vol. 106, pp. 506–516, Oct. 2018.
[23] M. Asgari-Chenaghlu, M. R. Feizi-Derakhshi, N. Nikzad-Khasmakhi, A. R. Feizi-Derakhshi, M. Ramezani, Z. Jahanbakhsh-Nagadeh, T. Rahkar-Farshi, E. Zafarani-Moattar, M. Ranjbar-Khadivi, M. A. Balafar, “Cy: Chaotic yolo for user intended image encryption and sharing in social media,” Information Sciences, vol. 542, pp. 212–227, Jan. 2021.
[24] H. Kaur, N. Sohi, “A study for applications of histogram in image enhancement,” The International Journal of Engineering and Science, vol. 6, no. 6, pp. 59–63, 2017.
[25] A. G. Asuero, A. Sayago, A. G. Gonzalez, “The correlation coefficient: An overview,” Critical reviews in analytical chemistry, vol. 36, no. 1, pp. 41–59, 2006.
[26] Y. Wu, Y. Zhou, G. Saveriades, S. Agaian, J. P. Noonan, P. Natarajan, “Local Shannon entropy measure with statistical tests for image randomness,” Information Sciences, vol. 222, pp. 323–342, Feb. 2013.
[27] Z. Hua, Y. Zhou, “Image encryption using 2D Logistic-adjusted-Sine map,” Information Sciences, vol. 339, pp. 237–253, Apr. 2016.
[28] H. Zhu, X. Zhang, H. Yu, C. Zhao, Z. Zhu, “An image encryption algorithm based on compound homogeneous hyper-chaotic system,” Nonlinear Dynamics, vol. 89, no. 1, pp. 61–79, Jul. 2017.
[29] Z. Hua, F. Jin, B. Xu, H. Huang, “2D Logistic-Sine-coupling map for image encryption,” Signal Processing, vol. 149, pp. 148–161, Aug. 2017.
[30] Z. Hua, Z. Zhu, S. Yi, Z. Zhang, H. Huang, “Cross-plane colour image encryption using a two-dimensional logistic tent modular map,” Information Sciences, vol. 546, pp. 1063–1083, Feb. 2021.
[31] R. M. May, “Simple Mathematical Models With Very Complicated Dynamics,” Nature, vol. 261, pp. 459–467, Jun. 1976.
[32] F. Hubertus, F. E. Udwadia, W. Proskurowski, “An efficient QR based method for the computation of Lyapunov exponents,” Physica D: Nonlinear Phenomena, vol. 101, no. 1–2, pp. 1–16, Feb. 1997.
[33] L. E. Bassham III, A. Rukhin, J. Soto, J. Nechvatal, M. Smid, E. Barker, S. Leigh, M. Levenson, M. Vangel, D. Banks, A. Heckert, J. Dray, S. Vo, “Sp 800-22 rev. 1a. a statistical test suite for random and pseudorandom number generators for cryptographic applications,” National Institute of Standards & Technology, Apr. 2010.
[34] G. Tang, X. Liao, Y. Chen, “A novel method for designing S-boxes based on chaotic maps,” Chaos Solitons & Fractals, vol. 23, no. 2, pp. 413–419 Jan. 2005.
[35] A. Belazi, M. Khan, A. A. Abd El-Latif, S. Belghith, “Efficient cryptosystem approaches: S-boxes and permutation–substitution-based encryption,” Nonlinear Dynamics, vol. 87, no. 1, pp. 337–361 Jan. 2017.
[36] J. Redmon, S. Divvala, R. Girshick, A. Farhadi, “You only look once: Unified, real-time object detection,” In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779–788, 2016.
[37] J. Redmon, A. Farhadi, “YOLO9000: better, faster, stronger,” In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263–7271, 2017.
[38] J. Redmon, A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
[39] O. Ronneberger, P. Fischer, T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” In International Conference on Medical image computing and computer-assisted intervention, Springer, pp. 234–241, Oct. 2015.
[40] G. Alvarez, S. Li, “Some basic cryptographic requirements for chaos-based cryptosystems,” International journal of bifurcation and chaos, vol. 16, no. 8, pp. 2129–2151, Aug. 2006.
[41] X. Chai, Y. Chen, L. Broyde, “A novel chaos-based image encryption algorithm using DNA sequence operations,” Optics and Lasers in engineering, vol. 88, pp. 197–213, Jun. 2017.
[42] D. Xiao, X. Liao, S. Deng, “One-way Hash function construction based on the chaotic map with changeable-parameter,” Chaos, Solitons & Fractals, vol. 24, no. 1, pp.65–71, Apr. 2005.
[43] Y. Zhang, D. Xiao, W. Wen, M. Li, “Breaking an image encryption algorithm based on hyper-chaotic system with only one round diffusion process,” Nonlinear Dynamics, vol. 76, no. 3, pp. 1645–1650, May. 2014.
[44] Y. Yang, L. Wang, S. Duan, L. Luo, “Dynamical analysis and image encryption application of a novel memristive hyperchaotic system,” Optics & Laser Technology, vol. 133, Jan. 2021.
[45] C. Fu, J. J. Chen, H. Zou, W. H. Meng, Y. F. Zhan, Y. W. Yu, “A chaos-based digital image encryption scheme with an improved diffusion strategy,” Optics express, vol. 20, no. 3, pp. 2363–2378, Jan. 2012.
[46] Y. Wu, J. P. Noonan, S. Agaian, “NPCR and UACI randomness tests for image encryption,” Journal of Selected Areas in Telecommunications, vol. 1, no. 2, pp.31–38, Apr. 2011.