Unsupervised Cipher Cracking Using Discrete GANs
This addresses cipher cracking for cryptography and security, but is incremental as it builds on CycleGAN for discrete data.
The paper tackles the problem of cracking ciphers like shift and Vigenere from unpaired ciphertext and plaintext using CipherGAN, achieving high fidelity and handling larger vocabularies than prior methods.
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.