A Novel SVM Based IDS for Distributed Denial of Sleep Strike in Wireless Sensor Networks

• DOI: 10.1007/s11277-019-06969-9
• Publication Date: 2019-11-25T18:02:37Z
• Authors: Noor Mohd; Annapurna Singh; H. S. Bhadauria
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; 7. Clean energy

It is well known that the safety, reliability and energy efficiencies are the prime concerns while designing and deploying wireless sensor networks. Therefore, unattained features and inability to recharge the nodes makes wireless sensor networks more susceptible to attack. To successfully deploy efficient usage of power resources, sensor networks from time to time keep nodes to sleep. They awake when some activity is noticed. MAC protocols playa very crucial role to save the power consumption during communication. Attacker is not adhering the communication protocols by taking the advantage of unattended scenario. The communication protocols are designed in such a manner that they are assuring the optimal consumption of battery or other power sources. By indulging the nodes in unnecessary communication adversary applies the repudiation of sleep attack by applying repudiation of service attack. This work implements the effect of denial of service attack which leads to the denial of sleep attack in wireless sensor networks using support vector machine learning. To achieve better result, model is developed and tested with the help of various kernel functions (linear, sigmoidal and redial functions). After the intensive execution of experiments, final outcomes have been drawn. On the basis of achieved results and validation of model we can conclude that the developed system performs outstanding throughput for detecting denial of sleep strike attack in WSN.