A team of researchers from the University of South Australia has created an artificial intelligence (AI) algorithm capable of detecting and stopping cyberattacks on military robots in mere seconds.

According to its developers, the algorithm employs deep learning neural networks to train a robot’s operating system, thus enabling it to recognize characteristics of a cyberattack, such as a man-in-the-middle attack wherein hackers intercept and alter communications.

Source: University of South Australia

The research team tested the AI algorithm on a replica of a U.S. Army combat ground vehicle, finding that the algorithm proved 99% effective at preventing such malicious attacks.

The University of South Australia suggested that the algorithm outperformed other tech currently used for detecting cyberattacks.

The algorithm is detailed in the article, Trusted Operations of a Military Ground Robot in the Face of Man-in-the-Middle Cyber-Attacks Using Deep Learning Convolutional Neural Networks: Real-Time Experimental Outcomes, which appears in the journal IEEE Transactions on Dependable and Secure Computing.