基于DPPO的双智能体协同渗透测试方法研究OA

The automated network penetration testing method based on reinforcement learning has received widespread attention in recent years.However,the existing research is mostly limited to small and medium-sized network environments,making it difficult to address the challenges posed by the vast number of hosts and complex topology in real-world networks.This study proposes a dual-agent collaborative pene-tration testing framework based on DPPO(Dual-agent Proximal Policy Optimization),which enhances the efficiency of attack decision-making in large-scale network environments through a division of labor and collaboration mechanism.The framework comprises a target decision-mak-ing agent(TargetDecider)and an attack execution agent(AttackExecutor),responsible for target node selection and specific vulnerability ex-ploitation execution,respectively.The two agents collaborate through shared environmental states,guided by a collaborative reward mecha-nism,to achieve division of labor and cooperation.Experiments were conducted in a simulated network environment built based on CyberBat-tleSim,and compared with traditional agent methods such as DQN,PPO,and SAC.The results show that the DPPO framework requires fe-wer steps and exhibits less fluctuation to compromise key targets,demonstrating higher attack efficiency and strategic stability.At the same time,its sensitive host compromise rate remains at a high level,indicating that the framework can reliably complete core penetration tasks.In terms of cumulative reward,DPPO also shows a trend of continuous optimization and robust convergence.The results indicate that the frame-work can effectively adapt to penetration testing tasks in large-scale static simulated networks,while its applicability to dynamic defense sce-narios and real network environments still requires further validation.