基于危险理论的无线传感器网络入侵检测模型  

Danger theory inspired intrusion detection model for wireless sensor networks

作　　者：傅蓉蓉[1] 郑康锋[2] 芦天亮[2] 杨义先[1,2] 

机构地区：[1]北京交通大学计算机与信息技术学院,北京100044 [2]北京邮电大学信息安全中心,北京100876

出　　处：《通信学报》2012年第9期31-37,共7页Journal on Communications

基　　金：国家科技重大专项基金资助项目(2011ZX03002-005-01);国家自然科学基金资助项目(61070204;61101108)~~

摘　　要：针对无线传感器网络入侵检测技术面临的挑战,利用了人工免疫技术的基本原理,提出一种基于危险理论的入侵检测模型。模型采用了分布式合作机制,与采用混杂模式监听获取全局知识的方法相比,在检测性能和能耗上都具有优势。仿真结果表明,相比于传统的单一阈值Watchdog算法和自我非我(SNS)模型,基于危险理论的检测模型能够提供较高的检测率和较低的误检率,并且有效降低了系统的能耗。According to the challenges of intrusion detection technique for wireless sensor networks,a danger theory in-spired intrusion detection model was proposed by taking advantage of the working principle of artificial immune system.Due to the distributed and cooperative mechanism,the proposed model shows more advantages in detection performance and energy consumption than methods adopt promiscuous mode to get global knowledge.The simulation results show that compared to traditional Watchdog algorithm with single threshold and self-nonself（SNS） model,the model inspired by danger theory can provide highest correct detection rate and lowest false detection rate.Moreover,the model can also decrease the energy consumption of the system.

关 键 词：无线传感器网络 入侵检测 人工免疫系统 危险理论 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]