Learning Attacker's Bounded Rationality Model in Security Games
Learning Attacker's Bounded Rationality Model in Security Games
复制标题
学习安全博弈中攻击者的有限理性模型
DOI：
10.1007/978-3-030-92307-5_62
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Jacek Ma'ndziuk
中科院分区：
文献类型：
--
作者：
A. Żychowski;Jacek Ma'ndziuk
提出了一种新的神经进化方法（NESG）来计算Stackelberg安全博弈中领导者的支付。NESG的核心是战略评估神经网络（SENN）。SENN能够有效地评估领导者的策略，而对手可能由于某些认知偏见或限制而不以完全理性的方式行事。SENN是在历史数据上训练的，不需要任何关于追随者的目标偏好、收益分布或有限理性模型的直接先验知识。NESG在一组90个基准游戏上进行了测试，这些游戏的灵感来自于被称为深度数据包检测的真实网络安全场景。实验结果表明，应用NESG的优势，现有的国家的最先进的方法时，发挥对不完全理性的对手。该方法提供了具有上级计算时间可扩展性的高质量解决方案。由于NESG的通用和无知识构造，该方法可以应用于各种现实生活中的安全场景。
The paper proposes a novel neuroevolutionary method (NESG) for calculating leader’s payoff in Stackelberg Security Games. The heart of NESG is strategy evaluation neural network (SENN). SENN is able to effectively evaluate leader’s strategies against an opponent who may potentially not behave in a perfectly rational way due to certain cognitive biases or limitations. SENN is trained on historical data and does not require any direct prior knowledge regarding the follower’s target preferences, payoff distribution or bounded rationality model. NESG was tested on a set of 90 benchmark games inspired by real-world cybersecurity scenario known as deep packet inspections. Experimental results show an advantage of applying NESG over the existing state-of-the-art methods when playing against not perfectly rational opponents. The method provides high quality solutions with superior computation time scalability. Due to generic and knowledge-free construction of NESG, the method may be applied to various real-life security scenarios.
快与慢的思考：跨时间尺度的优化分解
DOI：
10.1109/cdc.2017.8263834
发表时间：
2017
期刊：
56th IEEE Conference on Decision and Control
影响因子：
--
作者：
Goel, Gautam;Chen, Niangjun;Wierman, Adam
通讯作者：
Wierman, Adam