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 adobestock 444592786

Cyber Valley stands out at leading conference

Growing momentum with 23 accepted papers at the ICML
Arrow left
Thumb ticker md giraffe teaser400

Better decisions, more control: “Best Paper Award” for Tü...

Two Cyber Valley researchers awarded for best scientific paper at world-renowned confer...
Arrow left
Thumb ticker md giraffe teaser400

Better decisions, more control: “Best Paper Award” for Tü...

Two Cyber Valley researchers awarded for best scientific paper at world-renowned confer...
Arrow left