Reinforcement learning based self-adaptive moving target defense against DDoS attacks
Chungang Gao, Yongjie Wang · Journal of Physics Conference Series · 2021
Abstract In the research of moving target defense technology, the formulation and evaluation of network offensive and defensive game strategy have become a current research hotspot, but there are still some urgent problems to be solved, such as how to adjust the defense if the attacker’s strategy is constantly changing during the offensive and defensive game strategies to deal with its changes and how to balance system security and system performance when system resources are limited. Aiming at DDoS attacks, this paper proposes a moving target defense adaptive strategy based on reinforcement learning, which can adaptively adjust defense strategies according to changes in environmental conditions, while balancing system security and system performance through parameter adjustments to adapt to different scenarios. The simulation experiment results show that the proposed model and method are feasible and effective.