Researchers foil people-detecting AI with an 'adversarial' T-shirt

It's a well-established fact that object- and face-detecting algorithms are vulnerable to adversarial attack, as evidenced by a 2014 study conducted by researchers at Google and New York University. That's to say the models can be deceived by specially-crafted patches attached to real-world targets. Most research in adversarial attacks involves rigid objects like glass frames, stop signs, or cardboard. But scientists at Northwestern University and the MIT-IBM Watson AI Lab propose what they call an'adversarial' T-shirt, a t-shirt with a printed adversarial example that evades person detectors even when it's deformed by a wearer's changing pose. In a preprint paper, they claim that it manages to achieve up to 79% and 63% attack success rates in digital and physical worlds, respectively, against the popular YOLOv2 model.