Title :
Wireless sensor intrusion detection system based on the theory of evidence
Author :
Chang, Yonghu ; Liu, Feng
Author_Institution :
Coll. of Comput. & Inf. Sci., Southwest Univ., Chongqing, China
Abstract :
According to the feature that normal data and abnormal data in wireless sensor networks have no significant difference, this paper proposes intrusion detection model based on D-S evidence theory. Intrusion detection model views the standard deviation between data flow and historical data of each sensor as intrusion detection feature value, and then all these values treated as a group of data will be clustered. At last, the model fuses the clustering results by using D-S evidence theory to obtain a comprehensive assessment result, which can reflect the security of the sensor. The way of this algorithm to recognize the target is similar to human thinking, with high reliability, and has obvious advantages on computational complexity.
Keywords :
computational complexity; inference mechanisms; pattern clustering; security of data; telecommunication network reliability; telecommunication security; uncertainty handling; wireless sensor networks; D-S evidence theory; abnormal data feature; comprehensive assessment result; computational complexity; data clustering; data flow; intrusion detection feature value model; normal data feature; reliability; sensor security; wireless sensor network; Communication system security; Educational institutions; Hardware; Wireless communication; Wireless sensor networks; BPN; IDS; Wireless sensor network; evidence theory;
Conference_Titel :
Computer Science and Network Technology (ICCSNT), 2011 International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4577-1586-0
DOI :
10.1109/ICCSNT.2011.6182548