Abstract:
In developing wireless adhoc networks, several sorts of attacks represent serious
security problems.Various forms of attacks are currently being carried out against
various services and resources, with the goal of compromising their availability, confi dentiality, and integrity. Flooding based Denial of Service attacks has a serious impact
on Wireless Local Area Networks. It may result in clients being denied service. This
is a severe problem since it compromises one of the services offered by cyber security
such as availability. In ad-hoc networks, it is crucial to detect and block such attacks
in a timely manner. The objective of this thesis is to accurately detect and categorise
flooding attacks such as TCP, UDP, or ICMP. This thesis additionally categorises ad ditional assaults, such as U2R, R2L, and probe .The suggested method utilises various
supervised machine learning algorithms, including SVM, KNN, Naive Baye’s, Deci sion Tree, and Random Forest. Classification is performed using the NSL KDD data
set. The outcome demonstrated that RF classifier provides the highest performance
accuracy
