Research breakthrough possible @S-Logix pro@slogix.in

Office Address

  • 2nd Floor, #7a, High School Road, Secretariat Colony Ambattur, Chennai-600053 (Landmark: SRM School) Tamil Nadu, India
  • pro@slogix.in
  • +91- 81240 01111

Social List

Machine Learning Based Detection and a Novel EC-BRTT Algorithm Based Prevention of DoS Attacks in Wireless Sensor Networks - 2021

Machine Learning Based Detection and a Novel EC-BRTT Algorithm Based Prevention of DoS Attacks in Wireless Sensor Networks

Research Area:  Wireless Sensor Networks

Abstract:

Wireless sensor network allows nodes to communicate with another using wireless channels so that it is necessary for packet delivery to the nodes.Black hole attack occurs when a malicious node receives and misleads a set of nodes in the wireless network to drop the data they received.Wormhole attack occurs when malicious nodes create data delivery latency between two nodes in the wireless network.In this paper,we propose a Machine Learning based Naive Bayes Classifier to detect and Enhanced Code-based Round Trip Time based method prevent those two vital attacks. The black hole attack can be analyzed using this technique with the help of authorize code. Similarly,the wormhole attack and fake destination attack can be prevented by trip time to find the data delay time to reach the destination.In the case of black hole attack, a node which does not have authorized code will be considered as malicious node and discarded.If the packet does not arrive at the destination within the specific time, it will automatically detect the occurrence of wormhole in the wireless network. The proposed method is experimentally validated on network simulator (NS2).The main advantage of the proposed method is to reduce the communication overhead.

Keywords:  

Author(s) Name:  K. Lakshmi Narayanan,R. Santhana Krishnan,E. Golden Julie,Y. Harold Robinson,Vimal Shanmuganathan

Journal name:  Wireless Personal Communications

Conferrence name:  

Publisher name:  Springer

DOI:  10.1007/s11277-021-08277-7

Volume Information: