It’s about time. I mean, doesn’t it make you mad as all get out when someone hacks into your life? I know it does. Even spammers make you mad, so I’m happy someone has the ability to fight back. I’m talking about Artificial Intelligence robots and the wonderful people who create them. This article is about AI fighting back at hackers.
Researchers at ABB, Politecnico di Milano ( a French research university) and Trend Micro have been working a long time to find a way to combat hackers. They practiced on a few industrial robots owned by ABB, with permission, to see what they needed to come up with. They hacked into one robot that was supposed to be drawing straight lines in their production of a kit and caused it to make the line a few millimeters off. According to the robot, it was still drawing a straight line. It was just that the straight line was going in the wrong direction. Now if this was really happening in an automobile factory, think what that little bit of off-kelter part would do to the automobile. The auto would not be stable and would eventually cause an accident.
A while back, security consultancy IOActive discovered more than 50 vulnerabilities across a wide range of home and industrial robots. Rethink Robotics, maker of the Baxter and Sawyer models, patched the issues they were experiencing. They found several issues that could have left the machines open to remote attack.
It has become apparent that industrial robots can be hacked and the potential for catastrophe is very real. If an entire factory’s output is wasted because their robots were secretly caused to produce faulty goods, millions would be lost. And there’s the worse part about faulty parts for planes and cars that would make them dangerous if put out into the real world.
Trend Micro and Politecnico di Milano researchers used tools like Shodan to search for such connected machines and discovered more than 80,000 industrial routers used to control robots. They said such hacks are possible because thousands of robots are accessible on the Internet. The challenge is to keep bad things from happening when connected to the Internet. Because when you connect things to the Internet, bad things are now possible. Good things are also possible, like remotely checking the status of your home or business from halfway across the planet or updating things in real time, but attacks are remotely executable if there is an Internet connection. Hackers can pull this off.
The Georgia Institute of Technology researchers have created a little bot called HoneyBot that works very well against hackers. Hackers are lulled into a false sense of security and don’t realize they’re being attacked back when found out by the shoebox-sized bot. The researchers have designed a way for industrial companies to prevent their robots from being overtaken by cyber threats. They created HoneyBot to actually detect a cyber breach and alert its owners of the attack, all the while giving hackers the impression they’re still in control. But instead of giving up information, HoneyBot uses classic “honeypot” technology to lure in attackers and capture information about them, including their methods and even who and where they are.
The bot is still being tested, but researchers say its capabilities will become more and more important as devices that were never meant to operate on the Internet are being used factory wide. Raheem Beyah, professor and interim chair in Georgia Tech’s School of Electrical and Computer Engineering, says the biggest risk is more the cobots that operate freely on a factory floor and have the size and weight behind them to do considerable damage. Hacking is carried out relatively anonymously, so to be able to identify malicious actors would serve as a way to pin responsibility on those who want to harm an industrial operation. I’m saying it’s about time we fought back. You go, guys.