Machine Learning

Unsupervised Cipher Cracking Using Discrete GANs

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 9 months ago.


  • arXiv
    5 pts

    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.

    Unsupervised Cipher Cracking Using Discrete GANs
    by Aidan N. Gomez, Sicong Huang, Ivan Zhang, Bryan M. Li, Muhammad Osama, Lukasz Kaiser
    https://arxiv.org/pdf/1801.04883v1.pdf

You must be logged in to reply to this topic.