Cryptanalysis on double random phase encoding with deep learning

Random-phase-based optical image encryption techniques have drawn a lot of attention in recent years. However, in this contribution those schemes have been demonstrated to be vulnerable to chosen-plaintext attack (CPA) by employing the deep learning strategy. Specifically, by optimizing the parameters, the chosen deep neural network (DNN) can be trained to learn the sensing of an optical cryptosystem and thus get the ability to reconstruct any plaintext image from its corresponding ciphertext. A set of numerical simulation results have been further provided to shown its ability on cracking not only the classical double random phase encryption (DRPE), but also the tripe random-phase encryption (TRPE).

[1]  B Javidi,et al.  Optical image encryption based on input plane and Fourier plane random encoding. , 1995, Optics letters.

[2]  Xiang Peng,et al.  Asymmetric cryptosystem based on phase-truncated Fourier transforms. , 2010, Optics letters.

[3]  Yoshua Bengio,et al.  Deep Learning of Representations , 2013, Handbook on Neural Information Processing.

[4]  Guohai Situ,et al.  Deep-learning-based ghost imaging , 2017, Scientific Reports.

[5]  Osamu Matoba,et al.  Secure holographic memory by double-random polarization encryption. , 2004, Applied optics.

[6]  Justin Lee,et al.  Lensless computational imaging through deep learning , 2017, ArXiv.

[7]  Wenqi He,et al.  Ciphertext-only attack on optical cryptosystem with spatially incoherent illumination: from the view of imaging through scattering medium , 2017, Scientific Reports.

[8]  X C Cheng,et al.  Security enhancement of double-random phase encryption by amplitude modulation. , 2008, Optics letters.

[9]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[10]  Yibo Zhang,et al.  Deep Learning Microscopy , 2017, ArXiv.

[11]  Jingjuan Zhang,et al.  Double random-phase encoding in the Fresnel domain. , 2004, Optics letters.

[12]  Yu Zhang,et al.  Security enhancement of double random phase encoding using rear-mounted phase masking , 2018 .

[13]  Peng Zhang,et al.  Known-plaintext attack on optical encryption based on double random phase keys. , 2006, Optics letters.

[14]  Tara N. Sainath,et al.  The shared views of four research groups ) , 2012 .

[15]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[16]  Peng Zhang,et al.  Chosen-plaintext attack on lensless double-random phase encoding in the Fresnel domain. , 2006, Optics letters.

[17]  María J. Yzuel,et al.  Optical triple random-phase encryption , 2017 .

[18]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.