Header logo is avg

Thumb ticker 20191021 flowattack 15 klein
Von links nach rechts: Anurag Ranjan, Michael J. Black, Andreas Geiger and Joel Janai. Copyright: MPI-IS / W. Scheible

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.

Autonomous Cars Deep Neural Networks Computer Vision


ps Thumb sm pc1a5918
Anurag Ranjan
Ph.D. Student
avg ps Thumb sm joel small
Joel Janai
Ph.D. Student
avg ps Thumb sm upper body tiny
Andreas Geiger
Professor, University of Tübingen <br/ >Max Planck Research Group Leader
ps Thumb sm ports 160922 1261headcrop2
Michael Black
sg Thumb sm bildschirmfoto 2019 11 26 um 13.27.09
Linda Behringer
Public Relations