Researchers at Ben-Gurion University have devised a way to locate UAV operators
Develop a network-based neuron system that can predict the operator location on the UAV route only, without the need for additional sensors. Due to their agility, accessibility and low cost, UAVs pose a significant security risk
Mandy Kogosovsky | 8/07/2020 Contact author
print
send to a friend
A + A- size
Share on
Share on
BIGSTOCK / Copyright: MadPhotosPI
Cyber researchers at Ben-Gurion University of the Negev have developed a method for locating malicious UAV operators near airports or protected airspace by analyzing the UAV's flight path. The findings were presented as part of the Fourth International Symposium on Cyber Security, Cryptography and Machine Learning at the University. UAVs pose a significant security risk due to their agility, accessibility and low cost. As a result, there is a growing need to develop methods for detecting and reducing malicious actions.
"Right now, UAV operators can be found using RF technologies, which require sensors around the flight area," said lead researcher Elijah Bashadi, a university computer science student. "This situation poses challenges due to the widespread use of WiFi, other Bluetooth and IoT devices in the area, which block the UAV signals."
The researchers created a deep neuron network that could predict the position of the operators on the UAV path alone, without the need for additional sensors. In simulation tests, the model was able to predict the operator location with a precision of 78%. The next step in the project will be to repeat the experiment using data taken from real drones.
"Now that we know we can identify the location of the UAV operator, it will be interesting to see what additional data we can derive from this information," added Dr. Yossi Oren, senior lecturer in the Department of Software Engineering and Information Systems at Ben-Gurion University. "Possible insights will include the level of technical experience, and even the precise identity of the UAV operator."
https://www.israeldefense.co.il/he/node/43993
Develop a network-based neuron system that can predict the operator location on the UAV route only, without the need for additional sensors. Due to their agility, accessibility and low cost, UAVs pose a significant security risk
Mandy Kogosovsky | 8/07/2020 Contact author
send to a friend
A + A- size
Share on
Share on
BIGSTOCK / Copyright: MadPhotosPI
Cyber researchers at Ben-Gurion University of the Negev have developed a method for locating malicious UAV operators near airports or protected airspace by analyzing the UAV's flight path. The findings were presented as part of the Fourth International Symposium on Cyber Security, Cryptography and Machine Learning at the University. UAVs pose a significant security risk due to their agility, accessibility and low cost. As a result, there is a growing need to develop methods for detecting and reducing malicious actions.
"Right now, UAV operators can be found using RF technologies, which require sensors around the flight area," said lead researcher Elijah Bashadi, a university computer science student. "This situation poses challenges due to the widespread use of WiFi, other Bluetooth and IoT devices in the area, which block the UAV signals."
The researchers created a deep neuron network that could predict the position of the operators on the UAV path alone, without the need for additional sensors. In simulation tests, the model was able to predict the operator location with a precision of 78%. The next step in the project will be to repeat the experiment using data taken from real drones.
"Now that we know we can identify the location of the UAV operator, it will be interesting to see what additional data we can derive from this information," added Dr. Yossi Oren, senior lecturer in the Department of Software Engineering and Information Systems at Ben-Gurion University. "Possible insights will include the level of technical experience, and even the precise identity of the UAV operator."
https://www.israeldefense.co.il/he/node/43993
