Researchers developed an algorithm that can detect and shut down a man-in-the-middle (MitM) cyberattack on an autonomous military robot in seconds. When tested in real-time, the system has a 99% success rate.
Australian academics have developed an algorithm that can detect and shut down a man-in-the-middle (MitM) cyberattack on an autonomous military robot in seconds.
Artificial intelligence experts from Charles Sturt University and the University of South Australia (UniSA) trained the robot’s operating system to learn the signature of a MitM eavesdropping cyberattack in an experiment using deep learning neural networks to simulate the behavior of the human brain. This is when an attacker disrupts an ongoing communication or data transmission.
The robot operating system (ROS) is extremely susceptible to data breaches and electronic hijacking because it is so highly networked. The advent of Industry 4, marked by the evolution in robotics, automation, and the Internet of Things, has demanded that robots work collaboratively, where sensors, actuators, and controllers need to communicate and exchange information with one another via cloud services.
Professor Finn
The program was 99% successful in stopping a malicious attack when tested in real-time on a duplicate of a United States Army combat ground vehicle. The system’s effectiveness was demonstrated by false positive rates of less than 2%.
The findings were reported in the IEEE Transactions on Dependable and Secure Computing. Professor Anthony Finn, a UniSA autonomous systems researcher, claims that the suggested algorithm outperforms previous recognition algorithms used to detect cyberattacks around the world.
Professor Finn and Dr Fendy Santoso of Charles Sturt University’s Artificial Intelligence and Cyber Futures Institute worked with the US Army Futures Command to simulate a man-in-the-middle cyberattack on a GVT-BOT ground vehicle and train its operating system to detect an attack.
“The robot operating system (ROS) is extremely susceptible to data breaches and electronic hijacking because it is so highly networked,” Prof Finn says.
“The advent of Industry 4, marked by the evolution in robotics, automation, and the Internet of Things, has demanded that robots work collaboratively, where sensors, actuators, and controllers need to communicate and exchange information with one another via cloud services. The downside of this is that it makes them highly vulnerable to cyberattacks.”
“The good news, however, is that the speed of computing doubles every couple of years, and it is now possible to develop and implement sophisticated AI algorithms to guard systems against digital attacks.”
According to Dr. Santoso, despite its numerous advantages and widespread adoption, the robot operating system primarily ignores security vulnerabilities in its coding scheme due to encrypted network traffic data and insufficient integrity-checking capability.
“Owing to the benefits of deep learning, our intrusion detection framework is robust and highly accurate,” said Dr. Santoso. “The system can handle large datasets suitable to safeguard large-scale and real-time data-driven systems such as ROS.”
Prof Finn and Dr Santoso intend to test their intrusion detection system on several robotic platforms, including drones, which have faster and more complicated dynamics than terrestrial robots.
