From the link:
Depending on how paranoid you are, this research from Stanford and Google will be either terrifying or fascinating. [An AI or "agent"] intended to transform aerial images into street maps and back was found to be cheating by hiding information it would need later in “a nearly imperceptible, high-frequency signal.” Clever girl!
...
The intention of the researchers was...to accelerate and improve the process of turning satellite imagery into Google...maps. [T]he team was [used] a neural network that learns to transform images of type X and Y into one another, as efficiently yet accurately as possible, through a great deal of experimentation.
In some early results, the agent was doing well — suspiciously well. What tipped the team off was that, when the agent reconstructed aerial photographs from its street maps, there were lots of details that didn’t seem to be on the latter at all. For instance, skylights on a roof that were eliminated in the process of creating the street map would magically reappear when they asked the agent to do the reverse process....
Although it is very difficult to peer into the inner workings of a neural network’s processes [just like looking inside the human brain to see thoughts is "very difficult"], the team could easily audit the data it was generating [like listening to a human talk]. And with a little experimentation, they found that the agent had indeed pulled a fast one.
The intention was for the agent to be able to interpret the features of either type of map and match them to the correct features of the other. But what the agent was actually being graded on (among other things) was how close an aerial map was to the original, and the clarity of the street map.
So it didn’t learn how to make one from the other. It learned how to subtly encode the features of one into the noise patterns of the other [so it could accurately reproduce the original later for the scientists]. The details of the aerial map are secretly written into the actual visual data of the street map: thousands of tiny changes in color that the human eye wouldn’t notice, but that the computer can easily detect.
...
This practice of encoding data into images isn’t new; it’s an established science called steganography, and it’s used all the time to, say, watermark images or add metadata like camera settings. But a computer creating its own steganographic method to evade having to actually learn to perform the task at hand is rather new. ...
One could easily take this as a step in the “the machines are getting smarter” narrative.... [But, the] machine [didn't actually perform the task. Instead, it] found a way to cheat that humans are bad at detecting. ...
As always, computers do exactly what they are asked, so you have to be very specific in what you ask them. In this case the computer’s solution was an interesting one that shed light on a possible weakness of this type of neural network — that the computer, if not explicitly prevented from doing so, will essentially find a way to transmit details to itself in the interest of solving a given problem quickly and easily.
...
Link: https://techcrunch.com/2018/12/31/this-clever-ai-hid-data-from-its-creators-to-cheat-at-its-appointed-task/
(no message)