Drones – small commercial unmanned aerial systems or UASs – can be harmless toys, convenient devices to delivering pizza and even life-saving devices to find missing persons or catch speeders on highways. But it drones can also pose significant security risks when used by hostile forces such as terrorists. 

Researchers at Ben-Gurion University of the Negev (BGU) in Beersheba have now determined how to pinpoint the location of a drone operator who may be operating maliciously or harmfully near airports or protected airspace by analyzing the flight path of the drone. 

As drones are agile, accessible and inexpensive, there is a growing need to develop methods for detection, localization and neutralizing malicious and other harmful aircraft operation. Led by senior lecturer and drone expert Dr. Gera Weiss from BGU’s computer science department, the team explained their development at the Fourth International Symposium on Cyber Security, Cryptography and Machine Learning (CSCML 2020) on July 3rd. The speech was entitled: “Can the operator of a drone be located by following the drone’s path?”

“This paper presents our work towards autonomously localizing drone operators based only on following their path in the sky. We use a realistic simulation environment and collect the path of the drone when flown from different points of view.” 

“Currently, drone operators are located using radio frequency techniques and require sensors around the flight area that can then be triangulated,” says researcher Eliyahu Mashhadi, a BGU computer science student. “This is challenging due to the amount of other WiFi, Bluetooth and IoT [Internet of Things, a system of interrelated computing devices, mechanical and digital machines provided with unique identifiers and the ability to transfer data over a network without requiring human-to-human or human-to-computer interaction] signals in the air that obstruct drone signals” 

The researchers trained a deep neural network to predict the location of drone operators, using only the path of the drones, which doesn’t require more sensors. 

“Our system can now identify patterns in the drone’s route when the drone is in motion, and use it to locate the drone operator,” Mashhadi explained.

When tested in simulated drone paths, the model was able to predict the operator location with 78% accuracy. The next step in the project will be to repeat this experiment with data captured from real drones. “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, a senior lecturer in BGU’s software and information systems engineering department and head of the Implementation Security and Side-Channel Attacks Lab, who also contributed to the research. “Possible insights would include the technical experience level and even precise identity of the drone operator.”