USING DATA MINING TECHNIQUE AND MULTI OBJECTIVES CUCKOO SEARCH CLASSIFICATION FOR CLONE ATTACK DETECTION

Intrusion Detection Systems, as "IDSs," have been an essential component in Wireless Sensor Networks (WSNs) when it comes to identifying and thwarting attempts at breaching network security. In order to assure the dependability and safety of the services provided by WSN, modeling of IDS should be done in WSN. An approach to identifying different types of clone attacks in WSN has been developed as part of this body of work. To be more specific, an Adaptive random Forest based Multi-objective Cuckoo Search algorithm known as RF-MOCS has been developed with the intention of locating the origin of the clone assault utilizing the KDD cup dataset. In terms of accuracy, sensitivity, specificity, and F-measure, respectively, the suggested model demonstrates significant performance. When contrasted with other methods, such as ANN, Naive Bayes, and SVM, the suggested design exhibits superior trade-off characteristics