Cyber Algorithm Shuts Down Malicious Robotic Attack

University of South Australia

An algorithm developed by researchers at Australia’s Charles Sturt University and the University of South Australia (UniSA) was able to intercept and prevent a man-in-the-middle (MitM) eavesdropping cyberattack on an unmanned military robot within seconds. The researchers used deep learning neural networks to train the robot operating system (ROS) in a replica of a U.S. Army GVT-BOT ground vehicle to learn the signature of a MitM cyberattack. In real-time tests, the algorithm achieved a 99% success rate in preventing such attacks. UniSA’s Anthony Finn said the algorithm outperforms existing cyberattack recognition techniques. Added Charles Sturt University’s Fendy Santoso, “Owing to the benefits of deep learning, our intrusion detection framework is robust and highly accurate. The system can handle large datasets suitable to safeguard large-scale and real-time data-driven systems such as ROS.”

From “Cyber Algorithm Shuts Down Malicious Robotic Attack”
University of South Australia (10/12/23)
View Full Article