1.If you drop a white hat into the Red Sea,what does itbecome?2.What do people do in clock factories?3.Whv do seagulls live near the sea?4.A cowboy rode to an inn on Friday,stayed two nightsand 1eft on Friday.How coul...1.If you drop a white hat into the Red Sea,what does itbecome?2.What do people do in clock factories?3.Whv do seagulls live near the sea?4.A cowboy rode to an inn on Friday,stayed two nightsand 1eft on Friday.How could that be?5.Where does a bird go when it loses its tail?(Key:1.Wet.2.They make faces all day. 3.Because ifthey live near the bay they will be called bagels.4.Hishorse’s name was Friday.5.The retail store.)展开更多
Intelligent penetration testing is of great significance for the improvement of the security of information systems,and the critical issue is the planning of penetration test paths.In view of the difficulty for attack...Intelligent penetration testing is of great significance for the improvement of the security of information systems,and the critical issue is the planning of penetration test paths.In view of the difficulty for attackers to obtain complete network information in realistic network scenarios,Reinforcement Learning(RL)is a promising solution to discover the optimal penetration path under incomplete information about the target network.Existing RL-based methods are challenged by the sizeable discrete action space,which leads to difficulties in the convergence.Moreover,most methods still rely on experts’knowledge.To address these issues,this paper proposes a penetration path planning method based on reinforcement learning with episodic memory.First,the penetration testing problem is formally described in terms of reinforcement learning.To speed up the training process without specific prior knowledge,the proposed algorithm introduces episodic memory to store experienced advantageous strategies for the first time.Furthermore,the method offers an exploration strategy based on episodic memory to guide the agents in learning.The design makes full use of historical experience to achieve the purpose of reducing blind exploration and improving planning efficiency.Ultimately,comparison experiments are carried out with the existing RL-based methods.The results reveal that the proposed method has better convergence performance.The running time is reduced by more than 20%.展开更多
文摘1.If you drop a white hat into the Red Sea,what does itbecome?2.What do people do in clock factories?3.Whv do seagulls live near the sea?4.A cowboy rode to an inn on Friday,stayed two nightsand 1eft on Friday.How could that be?5.Where does a bird go when it loses its tail?(Key:1.Wet.2.They make faces all day. 3.Because ifthey live near the bay they will be called bagels.4.Hishorse’s name was Friday.5.The retail store.)
文摘Intelligent penetration testing is of great significance for the improvement of the security of information systems,and the critical issue is the planning of penetration test paths.In view of the difficulty for attackers to obtain complete network information in realistic network scenarios,Reinforcement Learning(RL)is a promising solution to discover the optimal penetration path under incomplete information about the target network.Existing RL-based methods are challenged by the sizeable discrete action space,which leads to difficulties in the convergence.Moreover,most methods still rely on experts’knowledge.To address these issues,this paper proposes a penetration path planning method based on reinforcement learning with episodic memory.First,the penetration testing problem is formally described in terms of reinforcement learning.To speed up the training process without specific prior knowledge,the proposed algorithm introduces episodic memory to store experienced advantageous strategies for the first time.Furthermore,the method offers an exploration strategy based on episodic memory to guide the agents in learning.The design makes full use of historical experience to achieve the purpose of reducing blind exploration and improving planning efficiency.Ultimately,comparison experiments are carried out with the existing RL-based methods.The results reveal that the proposed method has better convergence performance.The running time is reduced by more than 20%.
