Unsupervised Cipher Cracking Using Discrete GANs
arXiv:1801.04883
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.
References in corpus (11)
- Categorical Reparameterization with Gumbel-Softmax
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Improved Training of Wasserstein GANs
- Unsupervised Image-to-Image Translation Networks
- Text Understanding from Scratch
- Neural Machine Translation in Linear Time
- DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
- GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
- Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
- Least Squares Generative Adversarial Networks
- Boundary-Seeking Generative Adversarial Networks
Cited by in corpus (8)
- How Generative Adversarial Networks and Their Variants Work: An Overview
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization
- Unsupervised Text Style Transfer using Language Models as Discriminators
- Object Discovery with a Copy-Pasting GAN
- TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
- Learning to Read by Spelling: Towards Unsupervised Text Recognition
- Neuronal Learning Analysis using Cycle-Consistent Adversarial Networks