papers AI Learner
The Github is limit! Click to go to the new site.

Unsupervised Cipher Cracking Using Discrete GANs

2018-01-15
Aidan N. Gomez, Sicong Huang, Ivan Zhang, Bryan M. Li, Muhammad Osama, Lukasz Kaiser

Abstract

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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1801.04883

PDF

https://arxiv.org/pdf/1801.04883


Similar Posts

Comments