Color patch could throw self-driving vehicles off track

Researchers send wake-up call to the car industry

cyvy 24 October 2019 Press Release Max Planck Institute for Intelligent Systems, Tübingen, Germany Linda Behringer
Thumb ticker md 20191021 flowattack 15 klein

From left to right: Anurag Ranjan, Michael J. Black, Andreas Geiger und Joel Janai. Bildnachweis: MPI-IS / W. Sche...

A team of researchers in 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.

More Information

Video: