计算机科学
服务拒绝攻击
入侵检测系统
博弈论
纳什均衡
贝叶斯博弈
随机博弈
计算机安全
网络安全
互联网
重复博弈
数学优化
数理经济学
数学
万维网
作者
Logeswari Govindaraj,Bose Sundan,Anitha Thangasamy
标识
DOI:10.1109/iccct53315.2021.9711773
摘要
Distributed Denial-of-Service (DDoS) attacks pose a huge risk to the network and threaten its stability. A game theoretic approach for intrusion detection and prevention is proposed to avoid DDoS attacks in the internet. Game theory provides a control mechanism that automates the intrusion detection and prevention process within a network. In the proposed system, system-subject interaction is modeled as a 2-player Bayesian signaling zero sum game. The game's Nash Equilibrium gives a strategy for the attacker and the system such that neither can increase their payoff by changing their strategy unilaterally. Moreover, the Intent Objective and Strategy (IOS) of the attacker and the system are modeled and quantified using the concept of incentives. In the proposed system, the prevention subsystem consists of three important components namely a game engine, database and a search engine for computing the Nash equilibrium, to store and search the database for providing the optimum defense strategy. The framework proposed is validated via simulations using ns3 network simulator and has acquired over 80% detection rate, 90% prevention rate and 6% false positive alarms.
科研通智能强力驱动
Strongly Powered by AbleSci AI