A cunning AI cheated humans

Must Read

How to sync Google Drive with OneDrive

Nowadays, cloud storage is becoming more and more popular as a means of storing and backing up...

Apple TV+ is just $4.99 per month, free first year with new Apple products

The Apple Event 2019 took place on September 10th, 2019, in Cupertino, California. The event highlighted various upcoming...

Everything you need to know about iPhone 11, iPhone 11 Pro and Pro Max

Apple has announced iPhone 11, iPhone 11 Pro, and iPhone 11 Pro Max. The announcement was...
Avatar for Jazib Zaman
Fazeel Ashraf
IT graduate from Pakistan’s National University of Science and Technology with a passion for writing. When not reading or writing, I can be found listening to rock and metal or playing some classic jams on my electric guitar. I’m also a big fan of horror movies.

A machine learning algorithm intended to convert aerial images into street maps and vice versa has been caught cheating its creators. This algorithm has been created by researchers from Stanford and Google.

The AI was hiding data that it would require later in “a nearly imperceptible, high-frequency signal.” This incident is a remarkable, albeit a bit scary, occurrence. It breaks the golden rule of computing: computers follow a set of instructions, exactly as they are told.

The researchers wanted to speed up the process of incorporating satellite images into Google’s ever-reliable Maps. The team invented a CycleGAN neural network that converts the image into a Google Maps rendering.

CycleGAN’s goal is to carry out this procedure as accurately and efficiently as possible. The network has to learn through a lot of trial and error. CycleGAN was doing really well during the early testing phase. Then researchers figured that it was doing a bit too well.

For example, the software began reconstructing images from simplified street maps with details that were removed from the initial map layout. Specifically, the roofs of buildings with skylights that were removed while creating a street map would reappear out of thin air when the team instructed the AI to reverse the process.

Dissecting a neural network is no easy feat, but the team who invented the AI knew its inner workings quite well. The researchers were able to figure out the anomaly after running some quick tests. The AI’s goal was to quickly analyze how similar an aerial map was to the original street map. The tasks of creating a map rendering and turning it back into a photo were meant to be independent processes, but this showed that the computers were cheating by relying on data from the other set.

Instead of working harder, the AI was working smarter. The AI had figured out a clever shortcut that allowed it to reconstruct the aerial photo without having much knowledge about the street map.

Also ReadResearchers created an AI that can hack into biometrics

This is a feat in itself but wasn’t something the scientists were expecting. This is what made this discovery so profoundly interesting. The technique of turning data into images has existed for a while now, but a machine manipulating this technique isn’t something we see every day.

Technically speaking, the AI did its job, but it did it in a way that was completely out of the box. This discovery means engineers have to work harder at specifying the instructions they program onto machines.

If the instructions are more precise, machines should be able to perform tasks without finding innovative solutions. Since neural networks rely on machine learning, they are “open-ended” systems that are continuously learning and growing as information is fed to them.

This means neural networks are flawed by nature. Neural networks should not be implemented where specific tasks need to be solved in a specific manner. The research in this study was presented in a paper titled “CycleGAN, a Master of Steganography,” at the Neural Information Processing Systems conference in 2017.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Latest News

How to sync Google Drive with OneDrive

Nowadays, cloud storage is becoming more and more popular as a means of storing and backing up...

Apple TV+ is just $4.99 per month, free first year with new Apple products

The Apple Event 2019 took place on September 10th, 2019, in Cupertino, California. The event highlighted various upcoming releases by Apple, and one...

Everything you need to know about iPhone 11, iPhone 11 Pro and Pro Max

Apple has announced iPhone 11, iPhone 11 Pro, and iPhone 11 Pro Max. The announcement was made at Apple Event held...

Apple announces iPad 7th gen with Apple Pencil and keyboard support

The new Apple iPad 7 contains a 10.2-inch Retina display, compatibility with Apple Pencil and Smart Keyboard, offers great multitasking and creative power thanks to iPadOS.

Apple Event 2019: All announcements that matter

The most awaited event of the year took place yesterday, on September 10, 2019, at Apple's Spaceship campus in Cupertino, California....

More Articles Like This