Color patch could throw self-driving vehicles off track

Researchers send wake-up call to the car industry

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.

Video

Related Articles

Thumb ticker md 5

Amazon and Max Planck Society announce recipients of gift...

The awards support four research projects exploring the intersection of fashion and AI.
Arrow left
Thumb ticker md 240126 lab tour petra olschowsi img 1767 small size

Minister Olschowski visits Cyber Valley in Tübingen

Showcasing the future of intelligent systems and AI research
Arrow left
Thumb ticker md euroeap 2

EuroEAP 2024 comes to Stuttgart

Max Planck Institute for Intelligent Systems hosts international conference
Arrow left