Today's Hard|Forum Post
Today's Hard|Forum Post

Wednesday October 26, 2016

Google’s Neural Networks Invent Their Own Encryption

Researchers from Google Brain have discovered that machines can learn how to use basic encryption to keep their messages private. The obvious next step is machines learning how to secretly dispose of human bodies. Don't laugh, they are probably working on that as we speak.

Researchers Martأ­n Abadi and David Andersen demonstrate that neural networks, or "neural nets" آ– computing systems that are loosely based on artificial neurons آ– can work out how to use a simple encryption technique. In their experiment, computers were able to make their own form of encryption using machine learning, without being taught specific cryptographic algorithms. The encryption was very basic, especially compared to our current human-designed systems. Even so, it is still an interesting step for neural nets, which the authors state "are generally not meant to be great at cryptography".