IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Special Section on Cloud and Services Computing
Data Mining Intrusion Detection in Vehicular Ad Hoc Network
Xiaoyun LIUGongjun YANDanda B. RAWATShugang DENG
ジャーナル フリー

2014 年 E97.D 巻 7 号 p. 1719-1726


The past decade has witnessed a growing interest in vehicular networking. Initially motivated by traffic safety, vehicles equipped with computing, communication and sensing capabilities will be organized into ubiquitous and pervasive networks with a significant Internet presence while on the move. Large amount of data can be generated, collected, and processed on the vehicular networks. Big data on vehicular networks include useful and sensitive information which could be exploited by malicious intruders. But intrusion detection in vehicular networks is challenging because of its unique features of vehicular networks: short range wireless communication, large amount of nodes, and high mobility of nodes. Traditional methods are hard to detect intrusion in such sophisticated environment, especially when the attack pattern is unknown, therefore, it can result unacceptable false negative error rates. As a novel attempt, the main goal of this research is to apply data mining methodology to recognize known attacks and uncover unknown attacks in vehicular networks. We are the first to attempt to adapt data mining method for intrusion detection in vehicular networks. The main contributions include: 1) specially design a decentralized vehicle networks that provide scalable communication and data availability about network status; 2) applying two data mining models to show feasibility of automated intrusion detection system in vehicular networks; 3) find the detection patterns of unknown intrusions.

© 2014 The Institute of Electronics, Information and Communication Engineers
前の記事 次の記事