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 alexancder brem eni   gm

Brem among professors with strongest research record

Cyber Valley Professor in the top 15 of the “WirtschaftsWoche” Ranking
Arrow left
Thumb ticker md 20210723 mpiis students wolfram scheible 07

Great success at NeurIPS 2022

46 papers from Cyber Valley researchers selected for AI conference
Arrow left
Thumb ticker md schokoroboter und deepfakes cover

Chocolate robots and deepfakes

New comic of the Tübingen AI Center illustrates young people’s thoughts about AI
Arrow left