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 csm mvl6 69265d0977

Almost 20 million for Tübingen AI Center

Permanent funding for AI competence centers in Germany
Arrow left
News event item blue

Andreas Geiger wins Longuet-Higgins prize

Second high-profile award for the “KITTI Vision Benchmark”
Arrow left
Thumb ticker md imgl0231

Foundation stone laid for new Cyber Valley building

Structure to become part of the Innovation Campus in Tübingen
Arrow left