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 img 0126

Cyber Valley welcomes transatlantic delegation

State legislators from the U.S. and Germany visit Tübingen
Arrow left
Thumb ticker md start up network oct

Four new AI companies

Cyber Valley Start-up Network grows to 29 members
Arrow left
Thumb ticker md diabetes erkennung

Detect diabetes with whole-body MRI

Deep learning trained with over 2000 MRI images
Arrow left