Dein Suchergebnis zum Thema: Trainer

Colour patch could throw self-driving vehicles off track

https://www.mpg.de/14311323/colour-patch-could-throw-self-driving-vehicles-off-track

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 colour pattern to put the brakes on computer vision systems in autonomous cars.
self-driving technology that there is a new possible threat and enable them to train

Protecting ourselves against Internet manipulation

https://www.mpg.de/16408566/0211-bild-citizens-versus-the-internet-how-can-we-protect-ourselves-against-manipulation-fake-news-and-other-digital-challenges-149835-x

In the online world users’ attention is a precious currency, and online environments are designed to capture and steer that attention. Yet users and legislators currently have little to say in how these environments are regulated and controlled; How can we respond to these challenges of the digital age and how might the design of the online world be improved? A team of researchers addressed these questions from the perspective of behavioral science and now propose some answers.
They suggest that “boosting tools” can be used to train new competencies and enable

Attack on autopilots

https://www.mpg.de/14931044/attack-on-autopilots?c=12641819

How fast the development from assisted to fully automated vehicles will progress is uncertain. One crucial factor here is the reliability with which a vehicle can navigate in its surroundings and react to unforeseeable incidents. Our group at the Max Planck Institute for Intelligent Systems showed that methods for motion analysis based on deep neural networks – likely components in future autonomous vehicles – can be confused by small patterns designed to “attack” these networks.
Our work can help manufacturers to train their systems to withstand such disturbances

Attack on autopilots

https://www.mpg.de/14931044/attack-on-autopilots

How fast the development from assisted to fully automated vehicles will progress is uncertain. One crucial factor here is the reliability with which a vehicle can navigate in its surroundings and react to unforeseeable incidents. Our group at the Max Planck Institute for Intelligent Systems showed that methods for motion analysis based on deep neural networks – likely components in future autonomous vehicles – can be confused by small patterns designed to “attack” these networks.
Our work can help manufacturers to train their systems to withstand such disturbances