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.

With the increase of problem dimensions, most solutions of existing many-objective optimization algorithms are non-dominant. Therefore, the selection of individuals and the retention of elite individuals are important. Existing algorithms cannot provide sufficient solution precision and guarantee the diversity and convergence of solution sets when solving practical many-objective industrial problems. Thus, this work proposes an improved many-objective pigeon-inspired optimization (ImMAPIO) algorithm with multiple selection strategies to solve many-objective optimization problems. Multiple selection strategies integrating hypervolume, knee point, and vector angles are utilized to increase selection pressure to the true Pareto Front. Thus, the accuracy, convergence, and diversity of solutions are improved. ImMAPIO is applied to the DTLZ and WFG test functions with four to fifteen objectives and compared against NSGA-III, GrEA, MOEA/D, RVEA, and many-objective Pigeon-inspired optimization algorithm. Experimental results indicate the superiority of ImMAPIO on these test functions.