Deep Learning and Machine Learning Techniques for Intrusion Detection and Prevention in Wireless Sensor Networks: Comparative Study and Performance Analysis

Nowadays, there is remarkable growth in technology and wireless sensor networks. These are primarily used for the purpose of communication. Communication between devices may be wired or wireless, hence, the chance of attacks through the networks is increasing daily. For secure communication, intrusion detection and prevention are primary concerns. Thus, analyses of intrusion detection and prevention techniques have become an important part of the engineering field. With the assistance of intrusion detection and prevention system, we are able to determine and then notify the normal and abnormal activities of the users. Thus, there’s a requirement to design effective intrusion detection and prevention system by exploitation machine learning and deep learning for wireless sensor networks. In this work, a comparative study and performance analysis of different machine learning and deep learning techniques are given for intrusion detection and prevention system. The performance evaluation of these techniques is done by experiments conducted on WSN-DS dataset. The comparative analysis shows that deep learning classifiers shows better intrusion detection results than machine learning techniques. In this work, Convolutional Neural Network classifier is used.

[1]  Phayung Meesad,et al.  Incremental Learning Algorithm based on Support Vector Machine with Mahalanobis distance (ISVMM) for intrusion prevention , 2009, 2009 6th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[2]  Nilanjan Dey,et al.  Machine learning for medical diagnosis: A neural network classifier optimized via the directed bee colony optimization algorithm , 2019 .

[3]  Nilanjan Dey,et al.  Propagation analysis of MIMO ad hoc network in hybrid propagation model and implement less propagation loss algorithm to find the minimum loss route , 2016 .

[4]  Nour Moustafa,et al.  Identification of malicious activities in industrial internet of things based on deep learning models , 2018, J. Inf. Secur. Appl..

[5]  Ramjee Prasad,et al.  Proposed Security Model and Threat Taxonomy for the Internet of Things (IoT) , 2010, CNSA.

[6]  Nilanjan Dey,et al.  Flying Ad hoc Networks: A Comprehensive Survey , 2018 .

[7]  Nilanjan Dey,et al.  Secure minimum loss route selection of MIMO-based MANET in combined (indoor, outdoor, and forest) terrain , 2018, Int. J. Adv. Intell. Paradigms.

[8]  Dan Zhang,et al.  An efficient feature generation approach based on deep learning and feature selection techniques for traffic classification , 2018, Comput. Networks.

[9]  Le Thanh Sach,et al.  An anomaly-based network intrusion detection system using Deep learning , 2017, 2017 International Conference on System Science and Engineering (ICSSE).

[10]  Chunhua Wang,et al.  Machine Learning and Deep Learning Methods for Cybersecurity , 2018, IEEE Access.

[11]  Mousa Al-Akhras,et al.  WSN-DS: A Dataset for Intrusion Detection Systems in Wireless Sensor Networks , 2016, J. Sensors.

[12]  Nilanjan Dey,et al.  A Disaster Management Specific Mobility Model for Flying Ad-hoc Network , 2016, Int. J. Rough Sets Data Anal..

[13]  Nilanjan Dey,et al.  Applied Machine Learning for Smart Data Analysis , 2019 .

[14]  Nilanjan Dey,et al.  Soft Computing in Wireless Sensor Networks , 2018 .

[15]  Parikshit N. Mahalle,et al.  Decision Theory based Auto-delegation (DTA-d) scheme for Ubiquitous Computing , 2013 .

[16]  Yu Lasheng,et al.  Deep Learning Approach Combining Sparse Autoencoder With SVM for Network Intrusion Detection , 2018, IEEE Access.

[17]  Akshay Malhotra,et al.  A packet priority intimation-based data transmission for congestion free traffic management in wireless sensor networks , 2017, Comput. Electr. Eng..

[18]  Nilanjan Dey,et al.  Rough Set Based Ad Hoc Network: A Review , 2014, Int. J. Serv. Sci. Manag. Eng. Technol..

[19]  Nilanjan Dey,et al.  Classification Approach for Breast Cancer Detection Using Back Propagation Neural Network: A Study , 2016 .

[20]  Nilanjan Dey,et al.  Adaptative S3VM Semi Supervised Learning with Features Cooperation for Breast Cancer Classification , 2016 .

[21]  Nilanjan Dey,et al.  Recent Research on Multi Input Multi Output (MIMO) based Mobile ad hoc Network: A Review , 2014, Int. J. Serv. Sci. Manag. Eng. Technol..

[22]  Yuefei Zhu,et al.  A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks , 2017, IEEE Access.

[23]  Biju Issac,et al.  Performance Comparison of Intrusion Detection Systems and Application of Machine Learning to Snort System , 2017, Future Gener. Comput. Syst..

[24]  Nilanjan Dey,et al.  Predicting unusual energy consumption events from smart home sensor network by data stream mining with misclassified recall , 2018, J. Ambient Intell. Humaniz. Comput..

[25]  Nilanjan Dey,et al.  Implementation of a new packet broadcasting algorithm for MIMO equipped Mobile ad-hoc network , 2014, International Conference on Circuits, Communication, Control and Computing.

[26]  Qi Shi,et al.  A Deep Learning Approach to Network Intrusion Detection , 2018, IEEE Transactions on Emerging Topics in Computational Intelligence.

[27]  Nilanjan Dey,et al.  Convolutional Neural Network Based Clustering and Manifold Learning Method for Diabetic Plantar Pressure Imaging Dataset , 2017 .

[28]  M. A. Jabbar,et al.  Random Forest Modeling for Network Intrusion Detection System , 2016 .

[29]  Nilanjan Dey,et al.  Forest Type Classification: A Hybrid NN-GA Model Based Approach , 2016 .

[30]  Ahmed Toumanari,et al.  Intrusion Detection Techniques in Wireless Sensor Network using Data Mining Algorithms: Comparative Evaluation Based on Attacks Detection , 2015 .

[31]  Nilanjan Dey,et al.  Analysis of Performance of MIMO Ad Hoc Network in Terms of Information Efficiency , 2015 .

[32]  Ramjee Prasad,et al.  Identity Authentication and Capability Based Access Control (IACAC) for the Internet of Things , 2012, J. Cyber Secur. Mobil..