Date of Award

2011

Degree Type

Thesis

Degree Name

Bachelor of Computer Science Honours

School

School of Computer and Security Science

Faculty

Computing, Health and Science

First Advisor

Associate Professor Philip Hingston

Second Advisor

Dr Martin Masek

Abstract

This study has investigated novel Automated Red Teaming methods that support replanning. Traditional Automated Red Teaming (ART) approaches usually use evolutionary computing methods for evolving plans using simulations. A drawback of this method is the inability to change a team’s strategy part way through a simulation. This study focussed on a Monte-Carlo Tree Search (MCTS) method in an ART environment that supports re-planning to lead to better strategy decisions and a higher average score

Share

 
COinS