An Attack Graph Generation Method Based on Parallel Computing

Attack graph is used as a model that enumerates all possible attack paths based on a comprehensive analysis of multiple network configurations and vulnerability information. An attack graph generation method based on parallel computing is therefore proposed to solve the thorny problem of calculations as the network scale continues to expand. We utilize multilevel k-way partition algorithm to divide network topology into parts in efficiency of parallel computing and introduce Spark into the attack graph generation as a parallel computing platform. After the generation, we have a tool named Monitor to regenerate the attack graph of the changed target network. The method can improve the speed of calculations to solve large and complex computational problems and save time of generating the whole attack graph when the network changed. The experiments which had been done show that the algorithm proposed to this paper is more efficient benefiting from smaller communication overhead and better load balance.