Accurate Primary User Emulation Attack (PUEA) Detection in Cognitive Radio Network using KNN and ANN Classifier

Performance of a cognitive radio network (CRN) can be degraded by a primary user emulation attack (PUEA). Cognitive Radio (CR) is a potential answer for radio spectrum inefficiency issue. Primary user emulation (PUE) assault is a genuine risk to cognitive radio systems. This problem can be eliminated by disconnecting malicious user from base station after classification process. In this work, K nearest neighbor classifier (KNN) is used to classify the malicious users. KNN is trained by using parameters such data rate, distance, power, frequency of request etc. Also, proposed work is compared with artificial neural network (ANN) which is trained by the same parameters used for KNN training. Security of the network is improved by using Elliptical Curve Cryptography (ECC) as data encryption. Trained classifier can detect the emulating users with high accuracy due to significant parameter selection. To validate the performance, accuracy and sensitivity analysis are carried out, simulation results show that the proposed work performs better in terms of accuracy as compared to that of conventional PUEA classification techniques.