CB-D3QN: Malware Propagation Defense for Edge Intelligence Based Industrial Internet of Things via a Colonel Blotto Game-Enhanced Dueling Double Deep Q-Network Approach

Abstract

Malware spread in edge intelligence based Industrial Internet of Things (IIoT) systems is a serious challenge. Resources are unequal-attackers can put all their resources on one target, but defenders have to protect everything at once. To solve this challenge, we build CB-D3QN, which is a defense method using asymmetric Colonel Blotto game theory and Dueling Double Deep Q-Network (D3QN). We treat the fight between attackers and defenders as a Colonel Blotto game where both sides have different amounts of resources. This matches what happens in real IIoT malware attacks. CB-D3QN brings together Colonel Blotto games and D3QN, and uses deep reinforcement learning to find the right balance and make defense strategies better. The system considers malware behavior history, how we split resources, and which side has the advantage in each area. We evaluate CB-D3QN against other state-of-the-art methods and experimental results show that it achieves higher malware mitigation success rate, longer system resilience, and lower false intervention rate.