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 91

75 doctoral students join the Cyber Valley Innovation Campus

Bringing the next generation of AI experts to Baden-Württemberg
Arrow left
Thumb ticker md 20250314 tuebki oezdem olscho 48

Cem Özdemir visits Cyber Valley

The Federal Minister of Education and Research visits Cyber Valley and the Tübingen AI ...
Arrow left
Thumb ticker md design learnings graphics and comments 12

IMPRS-IS Call for Applications is Now Open

Join the Cyber Valley Community as a PhD student
Arrow left