Bi-population Genetic Algorithm-Based Attack Path Discovery Research in Large-scale Networks
Tairan Hu, Gao Wenlong, Tianyang Zhou, Zang Yichao · 2021
With the growth of network scale, present researches on the attack path discovery often encounter the problem of search space explosion that results in fails. To tackle the problem of attack path discovery for large-scale networks, this paper proposes a bi-population genetic algorithm for the attack path discovery in large-scale networks. Firstly, this paper represents the connective relationship between hosts as vectors and uses the Balanced Iterative Reducing and Clustering Using Hierarchies (Birch) algorithm to realize network decomposition. Then, the attack path discovery problem is encoded based on the decomposition result, and the bi-population mechanism is introduced to find the attack path. The experiment result shows that our algorithm performs better than Metric-FF and SGA in optimization and efficiency.