Authors :
Vijayaganth V.; Dharshana M.G.; Sureka P.; Varuna Priya S.
Volume/Issue :
Volume 9 - 2024, Issue 4 - April
Google Scholar :
https://tinyurl.com/36kar4rv
Scribd :
https://tinyurl.com/nhfrrcvs
DOI :
https://doi.org/10.38124/ijisrt/IJISRT24APR1128
Abstract :
There is a very bleak outlook on cyber
security due to the rapid expansion of the Internet and
the ever-changing terrain of cyber-attacks. This paper
explores the field of intrusion detection through network
analysis, with a particular emphasis on applying
machine learning (ML) and deep learning (DL)
approaches. For every ML/DL technique, a thorough
tutorial overview is given together with a review of
pertinent research publications. These studies were read,
indexed, and summarised according to their thermal or
temporal correlations with great care. The paper also
provides information on frequently used network
datasets in this field, which is relevant given the critical
role that data plays in ML/DL techniques. It also
discusses the difficulties in using ML/DL for cyber
security and provides insightful recommendations for
future lines of inquiry. Interestingly, the KDD data set
shows up as a reputable industry standard for intrusion
detection methods. A lot of work is being done to
improve intrusion detection techniques, and both
training and evaluating the detection model's quality
depend equally on the quality of the data. The KDD data
collection is thoroughly analysed in this research, with a
special emphasis on four different attribute classes:
Basic, Content, Traffic, and Host. We use the Modified
Random Forest (MRF) technique to classify these
properties.
Keywords :
Intrusion Detection, Feature Selection, Machine Leaning.
There is a very bleak outlook on cyber
security due to the rapid expansion of the Internet and
the ever-changing terrain of cyber-attacks. This paper
explores the field of intrusion detection through network
analysis, with a particular emphasis on applying
machine learning (ML) and deep learning (DL)
approaches. For every ML/DL technique, a thorough
tutorial overview is given together with a review of
pertinent research publications. These studies were read,
indexed, and summarised according to their thermal or
temporal correlations with great care. The paper also
provides information on frequently used network
datasets in this field, which is relevant given the critical
role that data plays in ML/DL techniques. It also
discusses the difficulties in using ML/DL for cyber
security and provides insightful recommendations for
future lines of inquiry. Interestingly, the KDD data set
shows up as a reputable industry standard for intrusion
detection methods. A lot of work is being done to
improve intrusion detection techniques, and both
training and evaluating the detection model's quality
depend equally on the quality of the data. The KDD data
collection is thoroughly analysed in this research, with a
special emphasis on four different attribute classes:
Basic, Content, Traffic, and Host. We use the Modified
Random Forest (MRF) technique to classify these
properties.
Keywords :
Intrusion Detection, Feature Selection, Machine Leaning.
