International Journal of Computer Networks and Applications

Prachi ¹

Affiliations
1 Department of CSE & IT, ITM University, Gurgaon, IN

Abstract

Security is a matter of extensive research interest with widespread deployment of WSN (Wireless Sensor Network) in various real life applications. Unreliable wireless communication, physically insecure locations and resource exhaustion attacks render sensor vulnerable to several security breaches. Sensors are supposed to operate on battery in hostile and unattended environment over a longer span of time. Taking into consideration conflict in interest between security and energy consumption, effective security implementation is non-trivial in WSN. A number of security schemes were presented in literature for ad hoc networks. However, most traditional security solutions like public key cryptography and trusted third party schemes are infeasible in WSN due to resource stringent nature. Probabilistic key management scheme (PKMS) perfectly suites the requirement of WSN due to their low storage, computation and communication overhead over resource stringent nodes. However, most the earlier presented PKMSs are based on Erdos-Renyi (ER) model of random graphs. ER model doesn't go along well with WSN due to their certain assumptions. In this paper, we present and implement a new PKMS scheme in TinyOS based on kryptograph model. Simulation results illustrate that scheme based on kryptograph model is more secure, memory efficient and connected when compared to scheme based on ER model.

Keywords

WSN, Security, Kryptograph, ER.

Full Text

   

Prachi ¹

Affiliations
1 Department of CSE & IT, The NorthCap University, IN

Abstract

Increase in volume and intensity of network attacks, forcing the business systems to revamp their network security solutions in order to avoid huge financial losses. Intrusion Detection Systems are one of the most essential security solutions in order to ensure the security of any network. Considering huge volumes of network data and complex nature of intrusions, the performance optimization of Network Intrusion Detection System became an open problem that is gaining more and more attention from the researchers nowadays. The objective of this paper is to identify a machine learning algorithm that provides high accuracy and real-time system application. This paper evaluates the performance of 15 different machine learning algorithms using NSL-KDD dataset on the basis of false discovery rate, average accuracy, ischolar_main mean squared error and model building time. Firstly, 5 machine learning algorithms out of 15 are chosen on the basis of maximum accuracy and minimum error in WEKA. Simulation of these machine learning algorithms is performed using 10-fold cross validation. Thereafter, the best machine learning algorithm is selected on the basis of maximum accuracy and minimum model building time so that it can be readily implemented in real-time Intrusion Detection Systems.

Keywords

Intrusion, Detection, Classification, Network, WEKA.

Full Text