Researchers at University of Washington, University of Michigan, Stony Brook University, and UC Berkeley have figured out how to hack self-driving cars by putting stickers on street signs.
Starting by analyzing the algorithm the vision system uses to classify images, they used a number of different attacks to manipulate signs in order to trick machine learning models into misreading them.
For instance, they printed up stickers to trick the vision system an autonomous car would use into reading a stop sign as a 45-mile-per-hour sign, the consequences of which would obviously be very bad in the real world.
In the paper, “Robust Physical-World Attacks on Machine Learning Models,” the authors demonstrated four different ways they were able to disrupt the way machines read and classify these signs using only a color printer and a camera. The most troubling part about these experiments is that they all appear very subtle to the human eye, camouflaged as graffiti, art, or incorporated into the sign’s imagery.
The first method involves printing up a full-size poster to cover the sign, which looks normal but maybe a little faded in places to a human. This caused the machine vision, from a number of angles and distances, to classify a stop sign as a speed limit sign 100 percent of the time in tests.
To read more of the original article, go to AutoBlog.
