Hi, this is Wayne again with a topic “The T-Shirt Invisibility Cloak”.
What, if I told you, you could defeat incredibly high-tech surveillance with a decidedly low-tech tool and no I’m not talking about spray painting, a security camera, I’m talking about simple clothing that can throw off Advanced, AI algorithms and facial recognition. It turns out that certain algorithms can be essentially reverse engineered in a manner that fools them, even if your face is in plain view. A few years ago, researchers at a university in Belgium took a closer look at a common image. Recognition algorithm called YOLO V2. It’S literally the name and worked out how to produce images that the algorithm either wouldn’t recognize as human or wouldn’t even recognize as any kind of object. The resulting images called adversarial patterns often resemble brightly colored, abstract art that the algorithm can’t make heads or tails of, but can any of us not only does this lead the algorithm to think there isn’t a person in the image at all, but the patterns also make For some pretty cool, looking clothing that there’s apparently already a market for some of the patterns effectively make the way are invisible to AI, While others make the computer think that it’s actually looking at something else like a dog. Of course, the method isn’t foolproof as a more sophisticated algorithm could get released at any time and would still recognize what it’s looking at and it won’t do. Much of an actual person is sitting on the other side of the security camera either. But there are other methods of hiding that don’t involve complicated, reverse engineering and we’ll tell you about them right after we think brilliant for sponsoring this video brilliant is a Hands-On and interactive way to learn stem topics. They offer thousands of courses with new topics to learn. Each month, like their Everyday Math course, their services can be used to supplement a college education or just to improve your overall body of knowledge.
The first 200 people who head to brilliant.org techwiki, will get 20 off an annual premium subscription. But why bother trying to be invisible to AI when you could just Spam it with noise, we’re starting to see clothing made to resemble other objects? The automated cameras commonly look for such as this address that’s covered with license plates, or this scarf with photorealistic faces. This way, you don’t have to beat its algorithm, you just feed it with junk data and you’re, also making a rather bold fashion statement. Of course, if you’re serious about remaining hidden, you could try this approach, which uses these masks that have a lens, like effect, to trick cameras, but keep you recognizable to fellow humans or even this prototype that projects different faces onto your own.
It’S like a scanner darkly, assuming that you can be bothered to wear something like that around town, but regardless of what method, anyone uses to fool an AI camera system, exactly how widespread are these surveillance technologies that researchers and designers have felt the need to explore ways To beat them actually more widespread than you might think. There have been plenty of headlines about how the authorities in mainland China have used smart cameras to track and identify citizens, but dozens of other countries are using similar Technologies for everything from cracking down on dissidents. To more benign Pursuits like traffic Management in smart cities and crowd security at sport, sporting events and these networks largely cannot function if they can’t even detect objects in the first place. Regardless of why you’re being spied on it’s understandable, if you want to try it and opt out while still being able to walk around a city center, but fair warning, even clothing, that utilizes adversarial patterns doesn’t work all the time even against image recognition, algorithms, it was Designed for, like maybe you’re, just standing kind of two sideways or something you know suddenly, setting up my own Society in the woods sounds pretty appealing thanks for watching guys if you like this video hit like hit, subscribe and hit us up in the comment section with Your suggestions for topics that we should cover in the future .