A Model for Anomaly Intrusion Detection with Different Feature Extraction Strategies in IoT

doi:10.3969/j.issn.1671-1122.2019.09.005

Abstract

Abstract:

In this paper, an intelligent intrusion detection system was proposed. We pay attention to the feature extraction problem which can make the detection model robust and improve the performance. A framework containing six different strategies is adopted. IDS in this paper was demonstrated using UNSW-NB15 dataset. The simulation results were quite satisfactory compared to some existing models.

Key words: IoT, anomaly intrusion detection, feature extraction, UNSW-NB15

CLC Number:

TP309

Jian KANG, Jie WANG, Zhengxu LI, Guangda ZHANG. A Model for Anomaly Intrusion Detection with Different Feature Extraction Strategies in IoT[J]. Netinfo Security, 2019, 19(9): 21-25.

Figures/Tables 5

References 13

[1]	SHAHZAD A A, KIM Y G, ELGAMOUDI A.Secure IoT Platform for Industrial Control Systems[C]//IEEE. 2017 International Conference on Platform Technology and Service(PlatCon), February 13-15, 2017, Busan, South Korea. New York: IEEE, 2017: 1-6.
[2]	SHERASIYA T, UPADHYAY H, PATEL H B.A Survey: Intrusion Detection System for Internet of Things[J]. International Journal of Computer Science and Engineering, 2016, 5(2): 91-98.
[3]	HE Xiang, LIU Sheng, JIANG Jiguo.Comparative Study of Intrusion Detection Methods Based on Machine Learning[J]. Netinfo Security, 2018, 18(5): 1-11.
	和湘,刘晟,姜吉国.基于机器学习的入侵检测方法对比研究[J].信息网络安全,2018,18(5):7-17.
[4]	MUNA A L H, MOUSTAFA N, SITNIKOVA E. Identification of Malicious Activities in Industrial Internet of Things Based on Deep Learning Models[EB/OL]. , 2019-1-22.
[5]	AMIRI F, YOUSEFI M M R, LUCAS C, et al. Mutual Information-based Feature Selection for Intrusion Detection Systems[J]. Journal of Network and Computer Applications, 2011, 34(4): 1184-1199.
[6]	MOUSTAFA N, SLAY J.A Hybrid Feature Selection for Network Intrusion Detection Systems: Central Points and Association Rules[C]//Joondalup Campus. 16th Australian Information Warfare Conference, November 30-December 2, 2015, Edith Cowan University, Perth, Western Australia. Western Australia: Edith Cowan University, 2015: 5-13.
[7]	BELOUCH M, EL HADAJ S, IDHAMMAD M.A Two-stage Classifier Approach Using Reptree Algorithm for Network Intrusion Detection[J]. International Journal of Advanced Computer Science and Applications, 2017, 8(6): 389-394.
[8]	ANWER H M, FAROUK M, ABDEL-HAMID A.A Framework for Efficient Network Anomaly Intrusion Detection with Features Selection[C]//IEEE. 9th International Conference on Information and Communication Systems, April 3-5, 2018, Irbid, Jordan. New York, IEEE, 2018: 157-162.
[9]	ELKHADIR Z, CHOUGDALI K, BENATTOU M.Intrusion Detection System Using PCA and Kernel PCA Methods[C]//Springer. The Mediterranean Conference on Information & Communication Technologies 2015, May 7-9, 2015, Saidia, Morocco. Heidelberg: Springer, 2016: 489-497.
[10]	LIN Weining, CHEN Mingzhi, ZHAN Yunqing, et al.Research on an Intrusion Detection Algorithm Based on PCA and Random-forest Classification[J]. Netinfo Security, 2017, 17(11): 50-54.
	林伟宁,陈明志,詹云清,等.一种基于PCA和随机森林分类的入侵检测算法研究[J].信息网络安全,2017,17(11):50-54.
[11]	HYVARINEN A.Fast and Robust Fixed-point Algorithms for Independent Component Analysis[J]. IEEE Transactions on Neural Networks, 2002, 10(3): 626-634.
[12]	ZOU Su, LI Chuanri, XU Fei, et al.Correlation Factor Analysis of FEA Model Simplification Methods of Printed Circuit Board[C]//IEEE. 7th International Conference on Computational Intelligence and Security, December 3-4, 2011, Hainan, China. New York: IEEE, 2011: 1461-1465.
[13]	MOUSTAFA N, SLAY J.The Significant Features of the UNSW-NB15 and the KDD99 Data Sets for Network Intrusion Detection Systems[C]//IEEE. 4th International Workshop on Building Analysis Datasets and Gathering Experience Returns for Security, November 5, 2015, Kyoto, Japan. New York: IEEE, 2015: 25-31.

实际预测	正常	攻击
正常	TN	FN
攻击	FP	TP

策略	序号	维度	准确率	Kappa系数
NB+FA	1	13	78.2%	0.546
RF+FA	2（100）	12	84.7%	0.477
	3（300）	12	84.7%	0.684
	4（500）	13	84.7%	0.682
NB+ICA	5	15	78.4%	0.549
RF+ICA	6（100）	11	86.0%	0.529
	7（300	11	86.1%	0.712
	8（500）	11	86.0%	0.711
NB+PCA	9	12	78.1%	0.548
RF+PCA	10（100）	11	85.5%	0.699
	11（300）	11	85.5%	0.700
	12（500）	11	85.4%	0.697

[1]	Lu CHEN, Yajie SUN, Liqiang ZHANG, Yun CHEN. A Scheme of Measurement for Terminal Equipment Based on DICE in IoT [J]. Netinfo Security, 2020, 20(4): 21-30.
[2]	Hui LI, Shice NI, Jia XIAO, Tianzhong ZHAO. Emotion Classification Technology for Online Video Comments on the Internet [J]. Netinfo Security, 2019, 19(5): 61-68.
[3]	Xudong WANG, Xiangzhan YU, Hongli ZHANG. Research on Traffic Identification Technology for Unknown Protocols [J]. Netinfo Security, 2019, 19(10): 74-83.
[4]	Weiping WEN, Jingwei LI, Yingnan JIAO, Hailin LI. A Vulnerability Detection Method Based on Random Detection Algorithm and Information Aggregation [J]. Netinfo Security, 2019, 19(1): 1-7.
[5]	LU Gang, GUO Ronghua, ZHOU Ying, WANG Jun. Review of Malicious Traffic Feature Extraction [J]. 信息网络安全, 2018, 18(9): 1-9.
[6]	REN Xiaoxian, CHEN Jie, LI Chenyang, YANG Yixian. Hazard Assessment of IoT Vulnerabilities Correlation Based on Risk Matrix [J]. 信息网络安全, 2018, 18(11): 81-88.
[7]	DUAN Guihua, SHEN Zhuoxiang, SHEN Dongjie, LI Zhi. Research on a Download Link Recognition Scheme Based on Feature Extraction [J]. 信息网络安全, 2018, 18(10): 31-36.
[8]	LI Zhicong, ZHOU Zhiping. Enhanced Secure RFID Authentication Protocol in IoT [J]. 信息网络安全, 2018, 18(1): 80-87.
[9]	WU Chuankun, ZHANG Lei, LI Jiangli. Design of Trust Architecture and Lightweight Authentication Scheme for IoT Devices [J]. 信息网络安全, 2017, 17(9): 16-20.
[10]	MA Guojun, BAI Lei, PEI Qingqi, LI Xiangjun. An End-to-End Security Scheme of the Internet of Things [J]. 信息网络安全, 2017, 17(10): 13-21.
[11]	PENG Kunlun, PENG Wei, WANG Dongxia, XING Qianqian. Research Survey on Security Issues in Cyber-Physical Systems [J]. 信息网络安全, 2016, 16(7): 20-28.
[12]	LIAO Jingxue, CHEN Fuzhen, CHENG Jiujun, CHEN Xiangrong. A Privacy Protection System for the Community IoT Innovative Technology and Service Platform [J]. 信息网络安全, 2016, 16(12): 60-67.
[13]	QIU Yue. Research on the Hidden Web Technology for the Network Content Security [J]. 信息网络安全, 2015, 15(9): 106-108.
[14]	ZHANG Xiao-hui, LIN Bo-gang. Research on Internet of Things Security Based on Support Vector Machines with Balanced Binary Decision Tree [J]. 信息网络安全, 2015, 15(8): 20-25.
[15]	ZHANG Yu-ting, YAN Cheng-hua, WEI Yu-ren. Research on Security of IoT Perception Layer Based on Node Authentication [J]. 信息网络安全, 2015, 15(11): 27-32.