ZTE

ZTE Communications ›› 2015, Vol. 13 ›› Issue (2): 7-11.DOI: 10.3969/j.issn.1673-5188.2015.02.002

• Special Topic • Previous Articles     Next Articles

An Instance-Learning-Based Intrusion-Detection System forWireless Sensor Networks

Shuai Fu1, Xiaoyan Wang2, and Jie Li1   

  1. 1. Department of Computer Science, University of Tsukuba, Tsukuba, Japan;
    Information Systems Architecture Science Research Division, National Institute of Informatics, Tokyo, Japan
  • Received:2015-04-10 Online:2015-06-25 Published:2015-06-25
  • About author:Shuai Fu (fs0818@gmail.com) received his MS degree in computer sceince from University of Tsukuba, Japan. He is currently a PhD candidate in the Department of Computer Science, University of Tsukuba. His research interests include security and mobility management in wireless networks.
    Xiaoyan Wang (wxyability@hotmail.com) received his BE degree from Beihang University, China, in 2004. He received his ME and PhD degrees from the University of Tsukuba, Japan, in 2010 and 2013. He is currently assistant professor in the Information Systems Architecture Science Research Division, National Institute of Informatics, Japan. His research interests include wireless communications and networks, with an emphasis on cognitive radio networks, game theory approaches, and cooperative communications.
    Jie Li (lijie@cs.tsukuba.ac.jp) received his BE degree in computer science from Zhejiang University, China. He received his ME degree in electronic engineering and communication systems from China Academy of Posts and Telecommunications, Beijing. He received his Dr. Eng. degree from the University of Electro-Communications, Japan. He is currently a profesor in the Department of Engineering, Information and Systems, University of Tsukuba, Japan. His research interests include mobile distributed computing and networking, network security, mobile cloud computing, OS, modeling and performance evaluation of information systems. He is a senior member of IEEE and ACM and a member of Information Processing Society of Japan. He has served as a secretary for Study Group on System Evaluation of IPSJ and has been on several editorial boards of IPSJ journals. He has been on the steering committees of the SIG of System EVAluation (EVA) of IPSJ, SIG of DataBase System (DBS) of IPSJ, and SIG of MoBiLe Computing and Ubiquitous Communications of IPSJ. He has co-chaired several international symposiums and workshops. He has also been in the program committees of several international conferences, including IEEE INFOCOM, IEEE ICDCS, IEEE ICC, IEEE GLOBECOM, and IEEE MASS.

An Instance-Learning-Based Intrusion-Detection System forWireless Sensor Networks

Shuai Fu1, Xiaoyan Wang2, and Jie Li1   

  1. 1. Department of Computer Science, University of Tsukuba, Tsukuba, Japan;
    Information Systems Architecture Science Research Division, National Institute of Informatics, Tokyo, Japan
  • 作者简介:Shuai Fu (fs0818@gmail.com) received his MS degree in computer sceince from University of Tsukuba, Japan. He is currently a PhD candidate in the Department of Computer Science, University of Tsukuba. His research interests include security and mobility management in wireless networks.
    Xiaoyan Wang (wxyability@hotmail.com) received his BE degree from Beihang University, China, in 2004. He received his ME and PhD degrees from the University of Tsukuba, Japan, in 2010 and 2013. He is currently assistant professor in the Information Systems Architecture Science Research Division, National Institute of Informatics, Japan. His research interests include wireless communications and networks, with an emphasis on cognitive radio networks, game theory approaches, and cooperative communications.
    Jie Li (lijie@cs.tsukuba.ac.jp) received his BE degree in computer science from Zhejiang University, China. He received his ME degree in electronic engineering and communication systems from China Academy of Posts and Telecommunications, Beijing. He received his Dr. Eng. degree from the University of Electro-Communications, Japan. He is currently a profesor in the Department of Engineering, Information and Systems, University of Tsukuba, Japan. His research interests include mobile distributed computing and networking, network security, mobile cloud computing, OS, modeling and performance evaluation of information systems. He is a senior member of IEEE and ACM and a member of Information Processing Society of Japan. He has served as a secretary for Study Group on System Evaluation of IPSJ and has been on several editorial boards of IPSJ journals. He has been on the steering committees of the SIG of System EVAluation (EVA) of IPSJ, SIG of DataBase System (DBS) of IPSJ, and SIG of MoBiLe Computing and Ubiquitous Communications of IPSJ. He has co-chaired several international symposiums and workshops. He has also been in the program committees of several international conferences, including IEEE INFOCOM, IEEE ICDCS, IEEE ICC, IEEE GLOBECOM, and IEEE MASS.

PDF

94

Abstract: This paper proposes an instance-learning-based intrusion-detection system (IL-IDS) for wireless sensor networks (WSNs). The goal of the proposed system is to detect routing attacks on a WSN. Taking an existing instance-learning algorithm for wired networks as our basis, we propose IL-IDS for handling routing security problems in a WSN. Attacks on a routing protocol for a WSN include black hole attack and sinkhole attack. The basic idea of our system is to differentiate the changes between secure instances and attack instances. Considering the limited resources of sensor nodes, the existing algorithm cannot be used directly in a WSN. Our system mainly comprises four parts: feature vector selection, threshold selection, instance data processing, and instance determination. We create a feature vector form composed of the attributes that changes obviously when an attack occurs within the network. For the data processing in resource-constrained sensor nodes, we propose a data-reduction scheme based on the clustering algorithm. For instance determination, we provide a threshold-selection scheme and describe the concrete-instance-determination mechanism of the system. Finally, we simulate and evaluate the proposed IL-IDS for different types of attacks.

Key words: WSN, security, intrusion-detection system, instance learning, black hole

摘要： This paper proposes an instance-learning-based intrusion-detection system (IL-IDS) for wireless sensor networks (WSNs). The goal of the proposed system is to detect routing attacks on a WSN. Taking an existing instance-learning algorithm for wired networks as our basis, we propose IL-IDS for handling routing security problems in a WSN. Attacks on a routing protocol for a WSN include black hole attack and sinkhole attack. The basic idea of our system is to differentiate the changes between secure instances and attack instances. Considering the limited resources of sensor nodes, the existing algorithm cannot be used directly in a WSN. Our system mainly comprises four parts: feature vector selection, threshold selection, instance data processing, and instance determination. We create a feature vector form composed of the attributes that changes obviously when an attack occurs within the network. For the data processing in resource-constrained sensor nodes, we propose a data-reduction scheme based on the clustering algorithm. For instance determination, we provide a threshold-selection scheme and describe the concrete-instance-determination mechanism of the system. Finally, we simulate and evaluate the proposed IL-IDS for different types of attacks.

关键词: WSN, security, intrusion-detection system, instance learning, black hole