Unsupervised Cipher Cracking Using Discrete GANs

This work details CipherGAN, an architecture inspired by CycleGAN used for inferring the underlying cipher mapping given banks of unpaired ciphertext and plaintext. We demonstrate that CipherGAN is capable of cracking language data enciphered using shift and Vigenere ciphers to a high degree of fidelity and for vocabularies much larger than previously achieved. We present how CycleGAN can be made compatible with discrete data and train in a stable way. We then prove that the technique used in CipherGAN avoids the common problem of uninformative discrimination associated with GANs applied to discrete data.

[1]  Kevin Knight,et al.  Unsupervised Analysis for Decipherment Problems , 2006, ACL.

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

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Mayank Dave,et al.  Genetic Algorithm and Tabu Search Attack on the Mono-Alphabetic Subsitution Cipher in Adhoc Networks , 2007 .

[5]  Yoshua Bengio,et al.  Boundary-Seeking Generative Adversarial Networks , 2017, ICLR 2017.

[6]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[7]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[8]  Xiang Zhang,et al.  Text Understanding from Scratch , 2015, ArXiv.

[9]  Ragheb Toemeh,et al.  Applying Genetic Algorithms for Searching Key-Space of Polyalphabetic Substitution Ciphers , 2008, Int. Arab J. Inf. Technol..

[10]  John M. Carroll,et al.  The Automated Cryptanalysis of Substitution Ciphers , 1986, Cryptologia.

[11]  S. S. Omran,et al.  A cryptanalytic attack on Vigenère cipher using genetic algorithm , 2011, 2011 IEEE Conference on Open Systems.

[12]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[13]  Kevin Knight,et al.  The Copiale Cipher , 2011, BUCC@ACL.

[14]  Reihaneh Safavi-Naini,et al.  Automated Cryptanalysis of Substitution Ciphers , 1993, Cryptologia.

[15]  Andrew M. Dai,et al.  Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step , 2017, ICLR.

[16]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

[17]  G. Athithan,et al.  An Automated Approach to Solve Simple Substitution Ciphers , 1993, Cryptologia.

[18]  Jacob D. Abernethy,et al.  How to Train Your DRAGAN , 2017, ArXiv.

[19]  Matt J. Kusner,et al.  GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution , 2016, ArXiv.

[20]  Alex Graves,et al.  Neural Machine Translation in Linear Time , 2016, ArXiv.

[21]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[22]  V.F. Kleist,et al.  The code book: the science of secrecy from ancient egypt to quantum cryptography [Book Review] , 2002, IEEE Annals of the History of Computing.

[23]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[24]  Jan Kautz,et al.  Unsupervised Image-to-Image Translation Networks , 2017, NIPS.

[25]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[26]  Camille Couprie,et al.  Semantic Segmentation using Adversarial Networks , 2016, NIPS 2016.

[27]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[28]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[29]  Zhen Wang,et al.  Multi-class Generative Adversarial Networks with the L2 Loss Function , 2016, ArXiv.

[30]  Prasad Kawthekar,et al.  Evaluating Generative Models for Text Generation , 2017 .

[31]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[32]  L PratapReddy,et al.  Decipherment of Substitution Cipher using Enhanced Probability Distribution , 2010 .

[33]  Yoshua Bengio,et al.  Maximum-Likelihood Augmented Discrete Generative Adversarial Networks , 2017, ArXiv.

[34]  Jacob Abernethy,et al.  On Convergence and Stability of GANs , 2018 .

[35]  Yee Whye Teh,et al.  The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables , 2016, ICLR.

[36]  Sam Hasinoff.  Solving Substitution Ciphers , 2007 .