Evolutionary computation techniques for intrusion detection in mobile ad hoc networks
Evolutionary computation techniques for intrusion detection in mobile ad hoc networks
复制标题
DOI：
10.1016/j.comnet.2011.07.001
复制
发表时间：
2011-10
期刊：
影响因子：
--
通讯作者：
Sevil Şen;John A. Clark
中科院分区：
文献类型：
--
作者：
Sevil Şen;John A. Clark
移动的自组织网络（adhoc networks，MANNETWORK）上的入侵检测是一个难点。这是因为它们的动态性、缺乏中心点以及资源高度受限的节点。在本文中，我们将探讨使用进化计算技术，特别是遗传编程和语法进化，进化入侵检测程序，这样具有挑战性的环境。认识到电源效率的特别重要性，我们分析了进化程序的功耗，并采用多目标进化算法来发现入侵检测能力和功耗之间的最佳权衡。
Intrusion detection on mobile ad hoc networks (MANETs) is difficult. This is because of their dynamic nature, the lack of central points, and their highly resource-constrained nodes. In this paper we explore the use of evolutionary computation techniques, particularly genetic programming and grammatical evolution, to evolve intrusion detection programs for such challenging environments. Cognizant of the particular importance of power efficiency we analyse the power consumption of evolved programs and employ a multi-objective evolutionary algorithm to discover optimal trade-offs between intrusion detection ability and power consumption.