Distributed AI Research Collaboration

About Us

We are a multi-disciplinary team of scientists and engineers.


Unsupervised Cipher Cracking Using Discrete GANs

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

Join The Team!

We're looking for graduate and undergraduate students globally with a background in computer science, mathematics and statistics to join the team remotely and help us realize our research projects.

If you're interested in deep learning and neural networks and have a foundation in calculus, statistics and software development then you're a perfect fit.

At present the team is unsalaried, but we do provide mentorship and authorship opportunities and we have a rich set of resources and training infrastructure at our disposal!

Email: team@for.ai with your resume and a brief note on your interest in ML and any relevant background (courses taken, projects completed, etc.)

Subscribe to our mailing list