Intrusion Detection Model Based on Feedforward Neural Network

doi:10.3969/j.issn.1671-1122.2019.09.021

Abstract

Abstract:

However, due to the diversity of intrusion behavior features and the complex network environment, intrusion detection methods based on deep learning are prone to have complex models and poor flexibility. To solve this problem, this paper proposed an intrusion detection model called SFID (Simplified Feedforward Intrusion Detection) based on feedforward neural network, which can integrate feature extraction and intrusion classification by reducing the number of neurons layer by layer, thus simplify the training complexity of intrusion detection model. With the verification, the training efficiency of this model is higher than that of S-NDAE model under the same accuracy.

Key words: intrusion detection, feedforward neural network, error backpropagation algorithm

CLC Number:

TP309

Wenying FENG, Xiaobo GUO, Yuanye HE, Cong XUE. Intrusion Detection Model Based on Feedforward Neural Network[J]. Netinfo Security, 2019, 19(9): 101-105.

Figures/Tables 3

References 18

[1]	JAVAID A Y, NIYAZ Q, SUN Weiqing, et al.A Deep Learning Approach for Network Intrusion Detection System[C]//ICST. 9th EAI International Conference on Bio-inspired Information and Communications Technologies, December 3-5, 2015, New York, USA. Brussels, Belgium: ICST, 2015: 21-26.
[2]	WANG Gang, HAO Jinxing, MA Jian, et al.A New Approach to Intrusion Detection Using Artificial Neural Networks and fuzzy clustering[J]. Expert Systems with Applications, 2010, 37(9): 6225-6232.
[3]	ALOM M Z, TAHA T M.Network Intrusion Detection for Cyber Security Using Unsupervised Deep Learning Approaches[C]//IEEE. National Aerospace and Electronics Conference(NAECON), June 27-30, 2017, Dayton, OH, USA. New York: IEEE, 2017, 63-69.
[4]	AMINANTO M E, KIM K.Improving Detection of Wi-Fi Impersonation by Fully Unsupervised Deep Learning[C]//Springer. 18th International Workshop on Information Security Applications, August 24-26, 2017, Jeju Island, Korea. Eerlin: Springer, 2017, 1-12.
[5]	AMINANTO M E, CHOI R, TANUWIDJAJA H C, et al.Deep Abstraction and Weighted Feature Selection for Wi-Fi Impersonation Detection[J]. IEEE Transactions on Information Forensics and Security, 2018, 13(3): 621-636.
[6]	AMINANTO M E, KIM K.Detecting Active Attacks in Wi-Fi Network by Semi-supervised Deep Learning[C]//Springer. Conference on Information Security and Cryptography 2017 Winter. November 29-December 1, 2017, Seoul, South Korea. Berlin: Springer, 2017: 1-4.
[7]	AMINANTO M E, KIM K.Detecting Impersonation Attack in WiFi Networks Using Deep Learning Approach[C]//Springer. 17th International Workshop on Information Security Applications. August 25-27, 2016, Jeju Island, Korea. Berlin: Springer, 2016: 1-12.
[8]	SALAMA M A, EID H F, RAMADAN R A, et al.Soft Computing in Industrial Applications[M]. Berlin: Springer, 2011.
[9]	DU Min, LI Feifei, ZHENG Guineng, et al.DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning[C]//ACM. the 2017 ACM SIGSAC Conference. October 30-November 3, 2017, Dallas, Texas, USA. New York: ACM, 2017: 1285-1298.
[10]	YIN C L, ZHU Y F, FEI J L, et al.A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks[J]. IEEE Access, 2017, 5(99): 21954-21961.
[11]	SHONE N, NGOC T N, PHAI V D, et al.A Deep Learning Approach to Network Intrusion Detection[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2018, 2(1): 41-50.
[12]	GAO Ni, GAO Ling, GAO Quanli, et al.An Intrusion Detection Model Based on Deep Belief Networks[C]//IEEE Computer Society. 2014 Second International Conference on Advanced Cloud and Big Data(CBD). November 20-22, 2014, Huangshan, China. New York: IEEE, 2014, 247-252.
[13]	ALRAWASHDEH K, PURDY C.Toward an Online Anomaly Intrusion Detection System Based on Deep Learning[C]//IEEE. IEEE International Conference on Machine Learning & Applications. December 18-20, 2016, California, USA. New York: IEEE, 2016: 195-200.
[14]	KIM J, KIM J, THU H L T, et al. Long Short Term Memory Recurrent Neural Network Classifier for Intrusion Detection[C]//IEEE. 2016 International Conference on Platform Technology and Service(PlatCon). February 15-17, 2016, Jeju, South Korea. New York: IEEE, 2016, 1-5.
[15]	LI Jing, WANG Bin.Network Intrusion Detection Method Based on Relevance Deep Learning[C]∥IEEE. 2016 International Conference on Intelligent Transportation, Big Data & Smart City(ICITBS). December 17-18, 2016, Changsha, China. New York: IEEE, 2016: 237-240.
[16]	ZHAO Guangzheng, ZHANG Cuixiao, ZHENG Lijuan.Intrusion Detection Using Deep Belief Network and Probabilistic Neural Network[C]//IEEE. 2017 IEEE International Conference on Computational Science and Engineering(CSE) and IEEE International Conference on Embedded and Ubiquitous Computing(EUC). July 22-23, 2017, Guangzhou, China. New York: IEEE, 2017: 639-642.
[17]	KANG M J, KANG J W.A Novel Intrusion Detection Method Using Deep Neural Network for In-Vehicle Network Security[C]//IEEE. 2016 IEEE 83rd Vehicular Technology Conference(VTC Spring). May 9-13, 2016, Nanjing, China. New York: IEEE, 2016: 1-5.
[18]	KIM K, MUHAMAD E A.Deep Learning in Intrusion Detection Perspective: Overview and Further Challenges[C]//IEEE. International Workshop on Big Data & Information Security. October 18-19, 2016, Jakarta, Indonesia. New York: IEEE, 2018: 5-10.

攻击类别	样本标签	KDD Cup 99数据集中该类攻击的样本数	NSL KDD数据集中该类攻击的样本数
Normal	normal	60593	67343
Probe	ipsweep mscan nmap portsweep saint satan	4166	11656
DoS	apache2 back land mailbomb neptune pod processtable smurf teardrop udpstorm	229853	45927
U2R	buffer_overflow httptunnel loadmodule perl ps rootkit sqlattack xterm	228	52
R2L	ftp_write guess_passwd imap multihop named phf sendmail snmpgetattack snmpguess spy warezclient warezmaster worm xlock xsnoop	16189	995
总计		311029	125973

数据集	测试集Loss	测试集Accuracy
KDD Cup 99	0.012	0.945
NSL KDD	0.026	0.928