Malicious drone operators could be found out by telltale flight path
Image credit: Pexels
Computer scientists from Ben-Gurion University of the Negev, Israel, have developed a method for pinpointing the location of a drone operator by analysing the flight path of their drone.
The technique could prove invaluable for tracking down malicious drone operators who fly their vehicles near airports or in protected airspace.
Due to their accessibility, there are now few barriers preventing people causing chaos and posing security risks using drones. In December 2018, there was disruption for thousands of passengers at Gatwick Airport due to a rogue operator (or operators) sending drones into the airspace. Heathrow and Gatwick later pledged to spend millions of pounds on anti-drone technology to prevent any similar disruption in the future.
Now, there is growing interest in methods for detecting and mitigating malicious drone operations. In September 2019, for instance, BT announced a “counter-drone programme” which uses a multi-sensor detection system to detect and monitor drones, which can then be tackled if necessary using tried-and-tested techniques such as signal jamming.
“Currently, drone operators are located using RF techniques and require sensors around the flight area which can then be triangulated,” said Eliyahu Mashhadi, a Ben-Gurion computer science student and lead researcher on the project. “This is challenging due to the amount of other Wi-Fi, Bluetooth, and IoT signals in the air that obstruct drone signals.”
Mashhadi and his colleagues trained a deep neural network to predict the location of drone operators using only the flight path of their drones, meaning that additional sensors were not required. They were able to train the system to identify certain patterns in flight paths which indicate the location of the operator.
When tested with simulated drone flight paths, the model was able to predict the location of the operator with 78 per cent accuracy. Next, the researchers will repeat and refine the experiment using data captured from real drones in flight.
“Now that we know we can identify the drone operator location, it would be interesting to explore what additional data can be extracted from this information,” said Dr Yossi Oren, who also contributed to the research.
“Possible insights would include the technical experience level and even precise identity of the drone operator.”
Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.