Color patch could throw self-driving vehicles off track

Researchers send wake-up call to the car industry

A team of researchers from the Max Planck Institute for Intelligent Systems and the University of Tübingen show that optical flow systems based on deep neural networks – a likely component of future autonomous cars – are vulnerable to adversarial attacks. The computer vision experts are shaking up the automotive industry by warning car manufacturers around the globe that it could take a simple color pattern to put the brakes on computer vision systems in autonomous cars.

Optical Flow,Car Industry,Computer Vision,ICCV,Michael J. Black,Andreas Geiger,Max Planck,autonomous driving,self-driving cars,automotive industry,autopilot,Perceiving Systems,