Intelligent fuzzy rule based Classification techniques for Intrusion detection and secure Routing in vanet

Abstract

Intelligent transportation systems, of which vehicular ad hoc newlinenetworks, or VANETs, are essential, have become part of everyday existence. newlineVANETs are subsets of MANETs that use automobiles as nodes for the newlinecreation of intelligent transportation networks. However, these networks are newlinevulnerable to attacks in view of vital applications like military use. Security newlinebreaches constitute a worry in view of aspects that includes high mobility, newlinechanging network topology, and coverage concerns. A safe routing method is newlinetherefore required for the prevention of attacks and guarantee of message newlinedelivery. In this work, training and testing models are created using the newlineUNSW-NB15 intrusion detection dataset. A unique intrusion detection system newlinethat categorizes the attacks based on the attributes using a feature selection newlinealgorithm is prescribed. The algorithm optimizes the identification of newlineanomalous activity while reducing related characteristics. This is newlineaccomplished by adding fuzzy-based rules to the Conditional Random Field newlinemethod, which leads to a highly effective feature selection process for the newlineidentification of impactful and contributory assaults like Denial-of-service newline(DoS), Worms, Fuzzers, and Shellcode. newline newline newline