E-mail Alert
RSS
| Citation: |
Liao MH, Zheng SS, Pan SX, Lu DJ, He WQ et al. Deep-learning-based ciphertext-only attack on optical double random phase encryption. Opto-Electron Adv 4, 200016 (2021). doi: 10.29026/oea.2021.200016
|
Original Article Open Access
Deep-learning-based ciphertext-only attack on optical double random phase encryption
-
Abstract
Optical cryptanalysis is essential to the further investigation of more secure optical cryptosystems. Learning-based attack of optical encryption eliminates the need for the retrieval of random phase keys of optical encryption systems but it is limited for practical applications since it requires a large set of plaintext-ciphertext pairs for the cryptosystem to be attacked. Here, we propose a two-step deep learning strategy for ciphertext-only attack (COA) on the classical double random phase encryption (DRPE). Specifically, we construct a virtual DRPE system to gather the training data. Besides, we divide the inverse problem in COA into two more specific inverse problems and employ two deep neural networks (DNNs) to respectively learn the removal of speckle noise in the autocorrelation domain and the de-correlation operation to retrieve the plaintext image. With these two trained DNNs at hand, we show that the plaintext can be predicted in real-time from an unknown ciphertext alone. The proposed learning-based COA method dispenses with not only the retrieval of random phase keys but also the invasive data acquisition of plaintext-ciphertext pairs in the DPRE system. Numerical simulations and optical experiments demonstrate the feasibility and effectiveness of the proposed learning-based COA method.-
Keywords:
- optical encryption /
- random phase encoding /
- ciphertext-only attack /
- deep learning
-
-
References
[1] Javidi B, Carnicer A, Yamaguchi M, Nomura T, Pérez-Cabré E et al. Roadmap on optical security. J Opt 18, 083001 (2016). doi: 10.1088/2040-8978/18/8/083001 [2] Carnicer A, Javidi B. Optical security and authentication using nanoscale and thin-film structures. Adv Opt Photonics 9, 218 (2017). doi: 10.1364/AOP.9.000218 [3] Refregier P, Javidi B. Optical image encryption based on input plane and Fourier plane random encoding. Opt Lett 20, 767–769 (1995). doi: 10.1364/OL.20.000767 [4] Unnikrishnan G, Joseph J, Singh K. Optical encryption by double-random phase encoding in the fractional Fourier domain. Opt Lett 25, 887–889 (2000). doi: 10.1364/OL.25.000887 [5] Zhu BH, Liu ST, Ran QW. Optical image encryption based on multifractional Fourier transforms. Opt Lett 25, 1159–1161 (2000). doi: 10.1364/OL.25.001159 [6] Situ GH, Zhang JJ. Double random-phase encoding in the Fresnel domain. Opt Lett 29, 1584–1586 (2004). doi: 10.1364/OL.29.001584 [7] Mehra I, Nishchal NK. Image fusion using wavelet transform and its application to asymmetric cryptosystem and hiding. Opt Express 22, 5474–5482 (2014). doi: 10.1364/OE.22.005474 [8] Javidi B, Nomura T. Securing information by use of digital holography. Opt Lett 25, 28–30 (2000). doi: 10.1364/OL.25.000028 [9] Kong DZ, Cao LC, Shen XJ, Zhang H, Jin GF. Image encryption based on interleaved computer-generated holograms. IEEE Trans Ind Inform 14, 673–678 (2018). doi: 10.1109/TII.2017.2714261 [10] Nomura T, Javidi B. Optical encryption using a joint transform correlator architecture. Opt Eng 39, 2031–2035 (2000). doi: 10.1117/1.1304844 [11] Zhang Y, Wang B. Optical image encryption based on interference. Opt Lett 33, 2443–2445 (2008). doi: 10.1364/OL.33.002443 [12] Chen W, Chen XD, Sheppard CJR. Optical image encryption based on diffractive imaging. Opt Lett 35, 3817–3819 (2010). doi: 10.1364/OL.35.003817 [13] Clemente P, Durán V, Torres-Company V, Tajahuerce E, Lancis J. Optical encryption based on computational ghost imaging. Opt Lett 35, 2391–2393 (2010). doi: 10.1364/OL.35.002391 [14] Shi YS, Li T, Wang YL, Gao QK, Zhang SG et al. Optical image encryption via ptychography. Opt Lett 38, 1425–1427 (2013). doi: 10.1364/OL.38.001425 [15] Schneier B. Applied Cryptography: Protocols, Algorithms, and Source Code in C 2nd ed (Wiley, New York, 1996). [16] Cheng XC, Cai LZ, Wang YR, Meng XF, Zhang H et al. Security enhancement of double-random phase encryption by amplitude modulation. Opt Lett 33, 1575–1577 (2008). doi: 10.1364/OL.33.001575 [17] Liao MH, He WQ, Lu DJ, Wu JC, Peng X. Security enhancement of the phase-shifting interferometry-based cryptosystem by independent random phase modulation in each exposure. Opt Lasers Eng 89, 34–39 (2017). doi: 10.1016/j.optlaseng.2016.03.015 [18] Sahoo SK, Tang DL, Dang C. Enhancing security of incoherent optical cryptosystem by a simple position-multiplexing technique and ultra-broadband illumination. Sci Rep 7, 17895 (2017). doi: 10.1038/s41598-017-17916-8 [19] Peng X, Wei HZ, Zhang P. Chosen-plaintext attack on lensless double-random phase encoding in the Fresnel domain. Opt Lett 31, 3261–3263 (2006). doi: 10.1364/OL.31.003261 [20] Liao MH, Lu DJ, He WQ, Peng X. Optical cryptanalysis method using wavefront shaping. IEEE Photonics J 9, 2200513 (2017). [21] Peng X, Zhang P, Wei HZ, Yu B. Known-plaintext attack on optical encryption based on double random phase keys. Opt Lett 31, 1044–1046 (2006). doi: 10.1364/OL.31.001044 [22] Gopinathan U, Monaghan DS, Naughton TJ, Sheridan JT. A known-plaintext heuristic attack on the Fourier plane encryption algorithm. Opt Express 14, 3181–3186 (2006). doi: 10.1364/OE.14.003181 [23] Peng X, Tang HQ, Tian JD. Ciphertext-only attack on double random phase encoding optical encryption system. Acta Phys Sin 56, 2629–2636 (2007). [24] Zhang CG, Liao MH, He WQ, Peng X. Ciphertext-only attack on a joint transform correlator encryption system. Opt Express 21, 28523–28530 (2013). doi: 10.1364/OE.21.028523 [25] Liu XL, Wu JC, He WQ, Liao MH, Zhang CG et al. Vulnerability to ciphertext-only attack of optical encryption scheme based on double random phase encoding. Opt Express 23, 18955–18968 (2015). doi: 10.1364/OE.23.018955 [26] Fienup JR. Reconstruction of an object from the modulus of its Fourier transform. Opt Lett 3, 27–29 (1978). doi: 10.1364/OL.3.000027 [27] Fienup JR. Phase retrieval algorithms: a comparison. Appl Opt 21, 2758–2769 (1982). doi: 10.1364/AO.21.002758 [28] Hayes M, Lim J, Oppenheim A. Signal reconstruction from phase or magnitude. IEEE Trans Acoust Speech Signal Process 28, 672–680 (1980). doi: 10.1109/TASSP.1980.1163463 [29] Michael G, Porat M. On signal reconstruction from Fourier magnitude. In Proceedings of the 8th IEEE International Conference on Electronics, Circuits and Systems 1403–1406 (IEEE, 2001). https://doi.org/10.1109/ICECS.2001.957477. [30] Sarang R, Motlagh MRJ, Eslami P. Reconstruction of image using just magnitude information of Fourier transform; is phase information really more important? In Proceedings of 2006 International Conference on Computational Inteligence for Modelling Control and Automation and International Conference on Intelligent Agents Web Technologies and International Commerce 56–56 (IEEE, 2006). http://doi.org/10.1109/CIMCA.2006.172. [31] Isernia T, Pascazio V, Pierri R, Schirinzi G. Image reconstruction from Fourier transform magnitude with applications to synthetic aperture radar imaging. J Opt Soc Am A 13, 922–934 (1996). doi: 10.1364/JOSAA.13.000922 [32] Gerchberg RW, Saxton WO. A practical algorithm for the determination of phase from image and diffraction plane pictures. Optik 35, 237–246 (1972). [33] Griffin D W, Lim J S. Signal estimation from modified short-time Fourier transform. IEEE Trans Acoust Speech Signal Process 32, 236–243 (1984). doi: 10.1109/TASSP.1984.1164317 [34] Shechtman Y, Eldar YC, Cohen O, Chapman HN, Miao JW et al. Phase retrieval with application to optical imaging: a contemporary overview. IEEE Signal Process Mag 32, 87–109 (2015). doi: 10.1109/MSP.2014.2352673 [35] Liao MH, He WQ, Lu DJ, Peng X. Ciphertext-only attack on optical cryptosystem with spatially incoherent illumination: from the view of imaging through scattering medium. Sci Rep 7, 41789 (2017). doi: 10.1038/srep41789 [36] Liao MH, Lu DJ, He WQ, Peng X. Speckle-correlation-based ciphertext-only attack on the double random phase encoding scheme. Proc SPIE 10250, 102502i (2017). [37] Li GW, Yang WQ, Li DY, Situ GH. Cyphertext-only attack on the double random-phase encryption: experimental demonstration. Opt Express 25, 8690–8697 (2017). doi: 10.1364/OE.25.008690 [38] Barbastathis G, Ozcan A, Situ GH. On the use of deep learning for computational imaging. Optica 6, 921–943 (2019). doi: 10.1364/OPTICA.6.000921 [39] Chen LW, Yin YM, Li Y, Hong MH. Multifunctional inverse sensing by spatial distribution characterization of scattering photons. Opto-Electron Adv 2, 190019 (2019). doi: 10.29026/oea.2019.190019 [40] Saetchnikov AV, Tcherniavskaia EA, Saetchnikov VA, Ostendorf A. Deep-learning powered whispering gallery mode sensor based on multiplexed imaging at fixed frequency. Opto-Electron Adv 3, 200048 (2020). doi: 10.29026/oea.2020.200048 [41] Kamilov US, Papadopoulos IN, Shoreh MH, Goy A, Vonesch C et al. Learning approach to optical tomography. Optica 2, 517–522 (2015). doi: 10.1364/OPTICA.2.000517 [42] Lyu M, Wang W, Wang H, Wang HC, Li GW et al. Deep-learning-based ghost imaging. Sci Rep 7, 17865 (2017). doi: 10.1038/s41598-017-18171-7 [43] Wang F, Wang H, Wang HC, Li GW, Situ GH. Learning from simulation: an end-to-end deep-learning approach for computational ghost imaging. Opt Express 27, 25560–25572 (2019). doi: 10.1364/OE.27.025560 [44] Zuo HR, Xu ZY, Zhang JL, Jia G. Visual tracking based on transfer learning of deep salience information. Opto-Electron Adv 3, 190018 (2020). doi: 10.29026/oea.2020.190018 [45] Rivenson Y, Zhang YB, Günaydın H, Teng D, Ozcan A. Phase recovery and holographic image reconstruction using deep learning in neural networks. Light Sci Appl 7, 17141 (2018). doi: 10.1038/lsa.2017.141 [46] Wang H, Lyu M, Situ GH. eHoloNet: a learning-based end-to-end approach for in-line digital holographic reconstruction. Opt Express 26, 22603–22614 (2018). doi: 10.1364/OE.26.022603 [47] Sinha A, Lee J, Li S, Barbastathis G. Lensless computational imaging through deep learning. Optica 4, 1117–1125 (2017). doi: 10.1364/OPTICA.4.001117 [48] Cherukara MJ, Nashed YSG, Harder RJ. Real-time coherent diffraction inversion using deep generative networks. Sci Rep 8, 16520 (2018). doi: 10.1038/s41598-018-34525-1 [49] Wang F, Bian YM, Wang HC, Lyu M, Pedrini G et al. Phase imaging with an untrained neural network. Light Sci Appl 9, 77 (2020). doi: 10.1038/s41377-020-0302-3 [50] Li S, Deng M, Lee J, Sinha A, Barbastathis G. Imaging through glass diffusers using densely connected convolutional networks. Optica 5, 803–813 (2018). doi: 10.1364/OPTICA.5.000803 [51] Li YZ, Xue YJ, Tian L. Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media. Optica 5, 1181–1190 (2018). doi: 10.1364/OPTICA.5.001181 [52] Metzler CA, Heide F, Rangarajan P, Balaji MM, Viswanath A et al. Deep-inverse correlography: towards real-time high-resolution non-line-of-sight imaging. Optica 7, 63–71 (2020). doi: 10.1364/OPTICA.374026 [53] Lyu M, Wang H, Li GW, Zheng SS, Situ GH. Learning-based lensless imaging through optically thick scattering media. Adv Photonics 1, 036002 (2019). [54] Hai H, Pan SX, Liao MH, Lu DJ, He WQ et al. Cryptanalysis of random-phase-encoding-based optical cryptosystem via deep learning. Opt Express 27, 21204–21213 (2019). doi: 10.1364/OE.27.021204 [55] Zhou LN, Xiao Y, Chen W. Machine-learning attacks on interference-based optical encryption: experimental demonstration. Opt Express 27, 26143–26154 (2019). doi: 10.1364/OE.27.026143 [56] Zhou LN, Xiao Y, Chen W. Vulnerability to machine learning attacks of optical encryption based on diffractive imaging. Opt Lasers Eng 125, 105858 (2020). doi: 10.1016/j.optlaseng.2019.105858 [57] Qin Y, Wan YH, Gong Q. Learning-based chosen-plaintext attack on diffractive-imaging-based encryption scheme. Opt Lasers Eng 127, 105979 (2020). doi: 10.1016/j.optlaseng.2019.105979 [58] Zhou LN, Xiao Y, Chen W. Learning-based attacks for detecting the vulnerability of computer-generated hologram based optical encryption. Opt Express 28, 2499–2510 (2020). doi: 10.1364/OE.380004 [59] Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention 234–241 (Springer, 2015). http://doi.org/10.1007/978-3-319-24574-4_28. [60] Zhang K, Zuo WM, Chen YJ, Meng DY, Zhang L. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 26, 3142–3155 (2017). doi: 10.1109/TIP.2017.2662206 [61] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE 86, 2278–2324 (1998). doi: 10.1109/5.726791 [62] Garris MD, Blue JL, Gerald TC, Grother PJ, Wilson CL. NIST Form-Based Handprint Recognition System (US Department of Commerce, Technology Administration, National Institute of Standards and Technology: Gaithersburg, MD, USA, 1997). [63] Ha D, Eck D. A neural representation of sketch drawings. arXiv: 1704.03477 (2017). -
Supplementary Information
Supplementary information for Deep-learning-based ciphertext-only attack on optical double random phase encryption
-
Access History
Figures(8)
Tables(1)
Article Metrics
Export File
Citation
Liao MH, Zheng SS, Pan SX, Lu DJ, He WQ et al. Deep-learning-based ciphertext-only attack on optical double random phase encryption. Opto-Electron Adv 4, 200016 (2021). doi: 10.29026/oea.2021.200016
Format
Content
DownLoad:
-
Figure 1.
Overview of learning-based COA on DRPE. (a) The encryption process of DRPE is a forward propagation process. (b) The COA is an inverse problem, aiming to obtain an optimized estimate of the plaintext from the ciphertext. (c) Flowchart of the proposed COA method, where two DNNs (DNN1 and DNN2) are used in serial to respectively learn the removal of speckle noise from the autocorrelation of the ciphertext Ac and the prediction of the final plaintext P from its autocorrelation Ap.
-
Figure 2.
Acquisition of the training data by designing a virtual DRPE system. A set of randomly generated RPMs (M1, M2,…,Mn) are placed at the spatial domain, and another set of randomly generated RPMs (N1, N2,…,Nn) are placed at the frequency domain. The ground truth plaintext images (P1, P2,…,Pn) are encrypted one-by-one and the corresponding ciphertext dataset (C1, C2,…,Cn) can be obtained.
-
Figure 3.
Structure of the employed DNNs. (a) The architecture of DNN1, which takes the DnCNN structure. (b) The architecture of DNN2, which takes the general encoder–decoder U-net structure. The encoder gradually condenses the lateral spatial information into high-level feature maps with growing depths; the decoder reverses the process by recombining the information into feature maps with gradually increased lateral details.
-
Figure 4.
Attack results by our proposed COA approach. (a) The given ciphertexts. (b) The autocorrelations of ciphertexts. (c) Outputs of DNN1. (d) Outputs of DNN2. (e) The ground-truth plaintext images.
-
Figure 5.
Quantitative evaluation of the reliability of the proposed COA method. (a) CC values to the number of tests. (b) The example of the prediction rotated 180 degrees and the ground-truth, which have the similar autocorrelation.
-
Figure 6.
Robustness test against cropping and noise. (a) Ciphertexts with cropping ratio 1/16 and 1/4, added zero-mean Gaussian noise with 0.01 and 0.02 variance, and added salt & pepper noise with 0.01 and 0.02 distribution density. (b) The corresponding autocorrelation distributions. (c) The retrieved images by the proposed two-step learning-based COA method. (d) The retrieved images by the one-step learning-based method.
-
Figure 7.
Experimental setup. SF: spatial filter, L1: collimating lens, L2: Fourier lens, P1 and P2: polarizers, RD: rotating diffuser, SLM: spatial light modulator.
-
Figure 8.
Experimental results. First column from left: the ground truth plaintext images “Apple” and “Banana”. Second column: the raw power spectrum images of the different types of diffusers. Third columns: the corresponding autocorrelation functions. Fourth and fifth columns: the recovered autocorrelation from DNN1 and the retrieved plaintext images from DNN2. Scale bar: 100 pixels in pictures of the second and third columns from left; 20 pixels in pictures of the first, fourth and fifth columns from left.
