Abstract:
With the growing rate of interconnections among computer systems, reliable
network communication is becoming a major
challenge. Intrusion detection has emerged as a
significant field of research, because it is not
theoretically possible to set up a system with no
vulnerabilities. This paper purposes the use of
fuzzy logic to generate decision tree to classify
the intrusion data. Further, the fuzzy decision
tree is then converted to fuzzy rules. The fuzzy
decision tree (C4.5) method is used the minimize
measure of classification ambiguity for different
attributes. This method overcomes the sharp
boundary problems; provide good accuracy
dealing with continuous attributes and prediction
problems. The experimental result is carried out
by using 10% KDD Cup 99 benchmark network
intrusion detection dataset.
