ARTÍCULO
TITULO

Pareto Optimal Solutions for Network Defense Strategy Selection Simulator in Multi-Objective Reinforcement Learning

Yang Sun    
Yun Li    
Wei Xiong    
Zhonghua Yao    
Krishna Moniz and Ahmed Zahir    

Resumen

Using Pareto optimization in Multi-Objective Reinforcement Learning (MORL) leads to better learning results for network defense games. This is particularly useful for network security agents, who must often balance several goals when choosing what action to take in defense of a network. If the defender knows his preferred reward distribution, the advantages of Pareto optimization can be retained by using a scalarization algorithm prior to the implementation of the MORL. In this paper, we simulate a network defense scenario by creating a multi-objective zero-sum game and using Pareto optimization and MORL to determine optimal solutions and compare those solutions to different scalarization approaches. We build a Pareto Defense Strategy Selection Simulator (PDSSS) system for assisting network administrators on decision-making, specifically, on defense strategy selection, and the experiment results show that the Satisficing Trade-Off Method (STOM) scalarization approach performs better than linear scalarization or GUESS method. The results of this paper can aid network security agents attempting to find an optimal defense policy for network security games.

 Artículos similares

       
 
D. ?. Vlasov,A. V. Sinchukov     Pág. 50 - 59
Possibilities of MS Excel in realization of various economic-mathematical methods united by the general problem of definition of an optimal solution are shown. First, Pareto's great number and optimization according to Pareto in the conditions of existen... ver más

 
Boris Melnikov,Tatyana Zubova     Pág. 1 - 8
In this article, we continue the description of mathematical models and algorithms designed to manage an organization based on value guidelines. We offer a fairly effective and at the same time universal algorithm for the integrated assessment and select... ver más

 
Weilin Liu, Lina Liu, Fang Tong     Pág. 1 - 15
There is an increasing trend in the use of multi-objective evolutionary algorithms (MOEAs) to solve multi-objective optimization problems of the allocation of water resources. However, typically the outcome is a set of Pareto optimal solutions which make... ver más
Revista: Water

 
Xujun Liu, Mengjiao Zhang, Han Su, Feifei Dong, Yao Ji, Yong Liu     Pág. 1 - 18
A multi-objective chance-constrained programming integrated with Genetic Algorithm and robustness evaluation methods was proposed to weigh the conflict between system investment against risk for watershed load reduction, which was firstly applied to nutr... ver más
Revista: Water

 
Jafar Yazdi, Young Hwan Choi, Joong Hoon Kim     Pág. 1 - 20
We developed a hybrid algorithm for multi-objective design of water distribution networks (WDNs) in the present study. The proposed algorithm combines the global search schemes of differential evolution (DE) with the local search capabilities of harmony ... ver más
Revista: Water