Google AI invents its own cryptographic algorithm; no one knows how it works

The study was a success: the first two AIs learnt how to communicate securely from scratch. P input plaintext, K shared key, C encrypted text, and PEve and PBob are the computed plaintext outputs.The Google Brain team (which is based out in Mountain View and is separate from in London) started with three fairly vanilla neural networks called Alice, Bob, and Eve. Each neural network was given a very specific goal: Alice had to send a secure message to Bob; Bob had to try and decrypt the message; and Eve had to try and eavesdrop on the message and try to decrypt it. Alice and Bob have one advantage over Eve: they start with a shared secret key (i.e. this is symmetric encryption). Importantly, the AIs were not told how to encrypt stuff, or what crypto techniques to use: they were just given a loss function (a failure condition), and then they got on with it.