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 cyber valley rebecca reisch web

Rebecca C. Reisch new Cyber Valley Managing Director

Science Minister Bauer: “Cyber Valley GmbH a central hub in the network”
Arrow left
Thumb ticker md microrobots

Microrobots display versatile movement patterns

System capable of quick transitions between behaviors
Arrow left
Thumb ticker md strahlen

Degree program combines radiation sciences with AI

New master’s profile at the University of Tübingen
Arrow left