Google’s Neural Networks Invent Their Own Encryption

[HardOCP News]

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 Martín Abadi and David Andersen demonstrate that neural networks, or “neural nets” – computing systems that are loosely based on artificial neurons – 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”.

 

[Twisted Kidney]

Great so there won't be any reprogramming the robots as they turn us into a thin layer of red paste to coat the land.

 

[[Spectre]]

Google, just rename the place Cyberdyne already.

 

[Zion Halcyon]

Ha, given how google has Clinton Foundation connections, you may not know how right you are...

 

[thesmokingman]

Why do these bots need to hide their messages???

 

[Spidey329]

Why do these bots need to hide their messages???

From spam and NSA bots!

 

[velusip]

Where do they even get this clipart?

 

[Whach]

Fine. Have a neural network. Just don't bloody well connect the damn thing to anything. Galactica style.

 

[dgz]

I don't trust no neural networks, or aliens, or robots.

But I've got a man with a name I can trust. Hugh Man