The AI that learnt to hide data from its creators to CHEAT at tasks they gave it

View
comments

New research from Stanford and Google has shown that it's possible artificial intelligence software may be getting too clever. 

The neural network, called CycleGAN, was trained to transform aerial images into street maps, then back into aerial images. 

Researchers were surprised when they discovered that details omitted in the final product reappeared when they told the AI to revert back to the original image. 

Scroll down for video   

For example, skylights on a roof that were absent from the final product suddenly reappeared when they returned to the original image, according to TechCrunch.  

'CycleGAN learns to "hide" information about a source image into the images it generates in a nearly imperceptible, high-frequency signal,' the study states. 

'This trick ensures that the generator can recover the original sample and thus satisfy the cyclic consistency requirement, while the generated image remains realistic.'

What ended up happening is that the AI figured out how to replicate details in a map by picking up on the subtle changes in color that the human eye can't detect, but that the computer can pick up on, TechCrunch noted. 

In effect, it didn't learn how

read more from dailymail.....