A team of researchers at the Google Brain office have been working on a project that involved creating three separate neural networks that between them have the ability to create and send encrypted messages. This type of machine learning will become more prominent in the world of AI over the next few years, particularly when it comes to handling private or sensitive information.
Two of the researchers involved, Martin Abadi and David Anderson, wrote in their paper that “The learning does not require prescribing a set of cryptographic algorithms, nor indicating ways of applying these algorithms: it is based only on a secrecy specification represented by the training objectives.” After several thousand simulations, Alice and Bob were each able to send and decrypt messages securely. Eve on the other hand, was unable to fully decrypt the messages.
The team then decided to create yet another neural network and this one they called Blind Eve. This neural network knew when information had been sent, but had no way of accessing it. The error rate of Blind Eve was higher but Eve came to a standstill after a while and could longer function efficiently. The researchers are now hoping to carry out more tests to see if it is a possibility that neural networks could be trained to protect sensitive and private data.
More News To Read
