A Self Organizing Map Intrusion Detection System for RPL Protocol Attacks

Routing over low power and lossy networks (RPL) is a standardized routing protocol for constrained Wireless Sensor Network (WSN) environments. The main node's constraints include processing capability, power, memory, and energy. RPL protocol describes how WSN nodes create a mesh topology, enabling them to route sensor data. Unfortunately, various attacks exist on the RPL protocol that can disrupt the topology and consume nodes' energy. In this article, the authors propose an intrusion detection system (IDS) based on self-organizing map (SOM) neural network to cluster the WSN routing attacks, and hence notify the system administrator at an early stage, reducing the risk of interrupting the network and consuming nodes' power. Results showed that the proposed SOM architecture is able to cluster routing packets into three different types of attacks, as well as clean data.

[1]  Mahdi Abadi,et al.  A PCA-based distributed approach for intrusion detection in wireless sensor networks , 2011, 2011 International Symposium on Computer Networks and Distributed Systems (CNDS).

[2]  Y.A. Sekercioglu,et al.  Detecting Selective Forwarding Attacks in Wireless Sensor Networks using Support Vector Machines , 2007, 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information.

[3]  John D. Hunter,et al.  Matplotlib: A 2D Graphics Environment , 2007, Computing in Science & Engineering.

[4]  Ashok Kumar Turuk,et al.  A Survey on Selective Forwarding Attack in Wireless Sensor Networks , 2011, 2011 International Conference on Devices and Communications (ICDeCom).

[5]  Wittek,et al.  somoclu : An Efficient Parallel Library for Self-Organizing Maps , 2016 .

[6]  Elie Nasr,et al.  An IoT approach to vehicle accident detection, reporting, and navigation , 2016, 2016 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET).

[7]  Djamel Tandjaoui,et al.  Analytical evaluation of the impacts of Sybil attacks against RPL under mobility , 2015, 2015 12th International Symposium on Programming and Systems (ISPS).

[8]  Wolf-Bastian Pöttner,et al.  IEEE 802 . 15 . 4 packet analysis with Wireshark and off-the-shelf hardware , 2010 .

[9]  Paul Honeine,et al.  Nonlinear adaptive filtering using kernel‐based algorithms with dictionary adaptation , 2015 .

[10]  Roger Achkar,et al.  Accurate Wavelet Neural Network for Efficient Controlling of an Active Magnetic Bearing System , 2010 .

[11]  Thiemo Voigt,et al.  SVELTE: Real-time intrusion detection in the Internet of Things , 2013, Ad Hoc Networks.

[12]  Fredrik Österlind,et al.  A Sensor Network Simulator for the Contiki OS , 2006 .

[13]  Jochen Wendel,et al.  Formalizing Guidelines for Building Meaningful Self-Organizing Maps , 2010 .

[14]  Roger Achkar,et al.  LPR CNN Cascade and Adaptive Deskewing , 2017 .

[15]  Jean-Philippe Vasseur,et al.  The Routing Protocol for Low-Power and Lossy Networks (RPL) Option for Carrying RPL Information in Data-Plane Datagrams , 2010, RFC.

[16]  Adam Dunkels,et al.  Powertrace: Network-level Power Profiling for Low-power Wireless Networks , 2011 .

[17]  Siarhei Kuryla,et al.  RPL: IPv6 Routing Protocol for Low power and Lossy Networks , 2010 .

[18]  Elie F. Kfoury,et al.  Generic hybrid methods for secure connections based on the integration of GBA and TLS/CA , 2017, 2017 Sensors Networks Smart and Emerging Technologies (SENSET).

[19]  Roger Achkar,et al.  Voice Identity Finder Using the Back Propagation Algorithm of an Artificial Neural Network , 2016 .