US12366434 - Apparatus and method for defending a predetermined area from an autonomously moving unmanned aerial vehicle

The patent describes a method for defending a designated area from autonomously moving unmanned aerial vehicles (UAVs) by generating adversarial examples to disrupt their machine-learning vision systems. It involves determining optimal positions for these examples based on geographical information and controlling defending UAVs to deploy them effectively.

Claim 1

1. A method for defending a predetermined area from an autonomously moving Unmanned Aerial Vehicle, UAV, the method comprising: generating one or more adversarial example adapted to disrupt a machine-learning based vision system of the UAV; determining, based on geographical information about at least one of the predetermined area and a surrounding area of the predetermined area, a respective position for the one or more adversarial example in at least one of the predetermined area and the surrounding area of the predetermined area; and controlling one or more defending UAV equipped with a respective one of the one or more adversarial example to fly at the respective determined position. generating one or more adversarial example adapted to disrupt a machine-learning based vision system of the UAV; determining, based on geographical information about at least one of the predetermined area and a surrounding area of the predetermined area, a respective position for the one or more adversarial example in at least one of the predetermined area and the surrounding area of the predetermined area; and controlling one or more defending UAV equipped with a respective one of the one or more adversarial example to fly at the respective determined position.

Google Patents

https://patents.google.com/patent/US12366434

USPTO PDF

https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/12366434