Implementing Lightweight IoT-IDS on Raspberry Pi Using Correlation-Based Feature Selection and Its Performance Evaluation

The application of many IoT devices is making our world more convenient and efficient. However, it also makes a large number of cyber-attacks possible because most IoT devices have very limited resources and cannot perform ordinary intrusion detection systems. How to implement efficient and lightweight IDS in IoT environments is a critically important and challenging task. Several detection systems have been implemented on Raspberry Pi, but most of them are signature-based and only allow limited rules. In this study, a lightweight IDS based on machine learning is implemented on a Raspberry Pi. To make the system lightweight, a correlation-based feature selection algorithm is applied to significantly reduce the number of features and a lightweight classifier is utilized. The performance of our system is examined in detail and the experimental result indicates that our system is lightweight and has a much higher detection speed with almost no sacrifice of detection accuracy.

[1]  Kjell Johnson,et al.  An Introduction to Feature Selection , 2013 .

[2]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[3]  Kouichi Sakurai,et al.  A Behavior-based Method for Detecting Distributed Scan Attacks in Darknets , 2013, J. Inf. Process..

[4]  A Min Tjoa,et al.  Performance Comparison between Naïve Bayes, Decision Tree and k-Nearest Neighbor in Searching Alternative Design in an Energy Simulation Tool , 2013 .

[5]  Francisco L. de Caldas Filho,et al.  Tracking intruders in IoT networks by means of DNS traffic analysis , 2017, 2017 Workshop on Communication Networks and Power Systems (WCNPS).

[6]  Michele Nogueira Lima,et al.  Detection of sinkhole attacks for supporting secure routing on 6LoWPAN for Internet of Things , 2015, 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM).

[7]  Ron Kohavi,et al.  Feature Subset Selection Using the Wrapper Method: Overfitting and Dynamic Search Space Topology , 1995, KDD.

[8]  Stephen D. Bay,et al.  The UCI KDD archive of large data sets for data mining research and experimentation , 2000, SKDD.

[9]  Liang Lu,et al.  Feature Selection for Machine Learning-Based Early Detection of Distributed Cyber Attacks , 2018, 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech).

[10]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[11]  Yuzhu Chen,et al.  Pi-IDS: evaluation of open-source intrusion detection systems on Raspberry Pi 2 , 2015, 2015 Second International Conference on Information Security and Cyber Forensics (InfoSec).

[12]  Salim Hariri,et al.  Enabling Risk Management for Smart Infrastructures with an Anomaly Behavior Analysis Intrusion Detection System , 2017, 2017 IEEE 2nd International Workshops on Foundations and Applications of Self* Systems (FAS*W).

[13]  Duncan Fyfe Gillies,et al.  A Review of Feature Selection and Feature Extraction Methods Applied on Microarray Data , 2015, Adv. Bioinformatics.

[14]  Jin Cao,et al.  An Automata Based Intrusion Detection Method for Internet of Things , 2017, Mob. Inf. Syst..

[15]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[16]  Nour Moustafa,et al.  UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set) , 2015, 2015 Military Communications and Information Systems Conference (MilCIS).

[17]  Mauro Conti,et al.  RPiDS: Raspberry Pi IDS — A Fruitful Intrusion Detection System for IoT , 2016, 2016 Intl IEEE Conferences on Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People, and Smart World Congress (UIC/ATC/ScalCom/CBDCom/IoP/SmartWorld).

[18]  Jill Slay,et al.  The Significant Features of the UNSW-NB15 and the KDD99 Data Sets for Network Intrusion Detection Systems , 2015, 2015 4th International Workshop on Building Analysis Datasets and Gathering Experience Returns for Security (BADGERS).

[19]  Deepak Sharma,et al.  HyINT: Signature-Anomaly Intrusion Detection System , 2018, 2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT).

[20]  Ian G. Harris,et al.  An efficient approach to prevent Battery Exhaustion Attack on BLE-based mesh networks , 2017, 2017 International Conference on Computing, Networking and Communications (ICNC).

[21]  Tomas Zitta,et al.  The security of RFID readers with IDS/IPS solution using Raspberry Pi , 2017, 2017 18th International Carpathian Control Conference (ICCC).

[22]  Rafael Fernandes Lopes,et al.  Poster Abstract: Real-Time DDoS Detection Based on Complex Event Processing for IoT , 2018, IoTDI.