New cyber algorithm shuts down malicious robotics attack

Researchers from Charles Sturt University and the University of South Australia have developed an algorithm capable of swiftly identifying and preventing man-in-the-middle (MitM) cyberattacks on unmanned military robots. In the experiment, deep learning neural networks mimicked human brain behavior to train a robot’s operating system to recognize MitM eavesdropping cyberattacks, which involve interrupting ongoing conversations or data transfers.
The algorithm, tested on a US army combat ground vehicle replica, had a 99% success rate in thwarting malicious attacks. The study showed false positive rates of less than 2%, validating the system’s effectiveness. The researchers now plan to test the intrusion detection algorithm on other robotic platforms, including drones.