BLACKSBURG, Va. (WFXR)– A Virginia Tech professor is using computer games, a common hobby for many across the United States, to enhance cybersecurity and Artificial Intelligence (AI).
Although computer games are considered a leisure activity, they can also be used as a training ground for AI to learn fundamental decision-making skills, handle uncertainty, and tackle complete interactions. AI has the ability to explore thousands of possibilities, making it the perfect tool for finding strategies that humans might overlook.
A professor from the Bradley Department of Electrical and Computer Engineering and entrepreneurship lead at Virginia Tech’s Innovation Campus, Angelos Stravrous, plans to use a multi-agent training exerciser (MATrEx) to boost AI’s impacts on security.
“What we want to do is take a network, like the Virginia Tech network, copy it into a virtual environment, and then run simulations of attacks and defenses with logic generated by AI agents,” said Stavrou, who’s also entrepreneurship lead for the Virginia Tech Innovation Campus. “AI can play billions of game variations so they can actually characterize the cybersecurity start of the system, and decide which attacks or defenses are superior.”
Within MATrEx, AI agents are grouped into two categories; red agents learning the gaming network and how best to break through system defenses for attacks, and blue agents that understand the network fully, including defense capabilities. The games are scenarios for red and blue agents to practice these methods against each other.
Radford University receives $1.2 to help hire student advocates supporting low-income students
What Stavrou and his team of researchers will be studying is AI’s reaction to different scenarios, including what attacks breakthrough, which defenses stop what attacks, and what happens during a specific attack.
“The idea is that we’ll create a loop, so the AI can play in a network that will start from a real network, then emulate it and simulate it,” said Stavrou. “The real system is accurate, but it’s slow. The simulation is fast, but it’s not as accurate. So you need to play the game across all these environments, transferring knowledge from the real network to the simulated. Then you transfer strategies from the simulated back to the real network.”
The end of this process is for MATrEx to scientifically assess both groups of agents. For red agents, MATrEx will see what new strategies they develop, and blue agents for how they outsmart their attackers.
Over the next four years, Stavrou is looking for more than AI to play games, but for MATrEx to serve as a cyber training ground where humans can also play, train, and learn about cybersecurity with a trained red agent built to win the game. He also wants to eventually incorporate students with hands-on training at the Innovation Campus.
“The goal of this project isn’t just to create a company, but to develop a company-university collaboration,” said Stavrou. “On the Innovation Campus, we’d like to have a space where we can showcase our work, a one-of-a-kind teaching lab for AI, for students to create projects. Really, we want it to be anything you can imagine.”
Copyright 2024 Nexstar Media, Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.
For the latest news, weather, sports, and streaming video, head to WFXRtv.
Source: VT professor using computer games to enhance AI cybersecurity defense
