BGU Identifies Malicious Drone Operators
July 9, 2020
By Charlie Osborne, an AABGU Fromson Fellow from the 2013 Murray Fromson Journalism Fellowship
ZDNet — BGU researchers have devised a way to pinpoint the location of drone operators seeking to cause harm or disruption in protected airspace.
When a few drones can cause chaos, being able to pinpoint the location of operators would be a blessing. Now, a BGU research team has demonstrated a potential means to do so.
In a research paper published this month, the BGU research team explored how analysis of flight paths may be useful in tracking malicious operators down.
Led by Prof. Gera Weiss of BGU’s Department of Computer Science and Dr. Yossi Oren from the Department of Software and Information Systems Engineering, the team attempted to tackle the problems associated with monitoring flight paths accurately, made more difficult due to the variety of electronic signals all around us.
“Currently, drone operators are located using RF techniques and require sensors around the flight area which can then be triangulated,” said lead researcher and computer science student Eliyahu Mashhadi. “This is challenging due to the amount of other Wi-Fi, Bluetooth, and IoT [internet of things] signals in the air that obstruct drone signals.”
The solution BGU came up with was the use of neutral networking.
Rather than focusing on trying to untangle a variety of signals, the network was trained to predict the location of an operator using only flight paths — even when in motion.
AirSim, an open-source, cross-platform simulator for drones was used to conduct the tests, using 10 km of roads and realistic obstacles such as buildings.
As shown below, the drone would be flown from point A to point B, and a data set containing 81 flights formed the basis of the network’s predictive modeling.
In total, the algorithms were able to predict the location of a drone operator with 78% accuracy during simulations, and while the experiment is small, the BGU research team indicates possible paths towards improvement include improving the machine learning pipeline or even attempts to gain insight into the skill level or training of an operator.
The research team now intends to repeat the experiments with drones in real-time.
The BGU research was presented at the Fourth International Symposium on Cyber Security, Cryptography and Machine Learning (CSCML 2020) on July 3.