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 3

Funded Doctoral Positions at the International Max Planck...

Doctoral training at the heart of the Cyber Valley Innovation Campus
Arrow left
Thumb ticker md hagel visits cyber valley

Manuel Hagel visits Cyber Valley

Baden-Württemberg’s global role in AI innovation
Arrow left
Thumb ticker md 2025.05.15 mpi spatenstich 1

Groundbreaking Ceremony for the Cyber Valley Building in ...

Laying the Foundation for Europe’s AI Future
Arrow left