How Google's AI taught itself to create its own encryption

How Google’s AI taught itself to create its own encryption

Monday 31 October 2016 Shutterstock As machine learning becomes ubiquitous, robots will be tasked with handling increasingly more sensitive and private data. In order to help protect this personal information, computer scientists at Google have developed neural networks that teach themselves how to encrypt the information they process. ADVERTISEMENT A team from Google Brain, the organisation’s deep learning research project, taught neural networks how to encrypt and decrypt messages. In a research paper published online the scientists created three neural networks: Alice, Bob, and Eve. Each was assigned its own job. Alice was taught to send secret, encrypted, messages to Bob. Bob was required to try to decrypt them. Finally, Eve, was taught to decypher the messages, without being given the secret key provided to the other neural networks. None…


Link to Full Article: How Google’s AI taught itself to create its own encryption