AI can help protect vital networks, say experts
International experts in artificial intelligence have proposed using AI to help protect critical infrastructure including power, water and communication networks.
The Flinders University and Brazilian experts have worked on a new model to provide early identification of software virus attack, hacker activity or general system failure in vital networks millions of people rely on every day.
Dr. Paulo Santos, Associate Professor in Artificial Intelligence and Robotics at Flinders University, said the new algorithm is capable of detecting failures in data networks that are robust to inconsistencies in the sensor data.
"This could be advanced to be an effective safeguard against equipment failures in data networks of electrical systems and could replace more traditional diagnostic methods both in power and other critical infrastructure," he said.
"It is one of the first complete investigation of this system of testing paraconsistent analyzers in a large simulation of a complex electrical system."
Paraconsistent analyzers are a type of AI that can deal with conflicting information. This is important in critical infrastructure systems where there is often a lot of data coming from different sources, some of which may be contradictory.
The new algorithm developed by the Flinders University and Brazilian experts is able to filter out conflicting information and identify the most likely cause of a problem. This could help to prevent major disruptions to critical infrastructure systems.
The researchers say that AI could be used to improve software applications and other fault diagnostic systems that help prevent errors in complex engineering systems, or manufacturing plants, and other critical infrastructure.
"Already data analysis, machine learning and rule-based learning are used to develop fault diagnostic systems," said Dr. Santos.
"However, we have expanded on these approaches to add an 'evidence filter' to the process of system diagnostics to take into account conflicting evidence by considering a degree of trust in the sensor data."
With further development, the new model of analysis developed by the researchers could be consolidated to address ever more sophisticated technological failures in critical systems which support major industries, entire urban networks, and so on.
The findings of the research have been published in a new article in the journal Expert Systems with Applications.