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 ku%cc%88nstliche organe w scheible 1 1

Organ twin: a “flight simulator” for surgeons

Intelligent artificial organs enhance training and quality of surgery
Arrow left
Thumb ticker md decode cos 7 cell

Machine learning improves biological image analysis

International team develops algorithm that accelerates super-resolution microscopy
Arrow left
Thumb ticker md imprs

Funded Ph.D. positions at the IMPRS-IS

Apply to join the program and begin a Ph.D. in 2022
Arrow left