Enhancing Intrusion Detection Performance with a Hybrid Module on KDD99 Dataset

Preview this chapter:

Enhancing Intrusion Detection Performance with a Hybrid Module on KDD99 Dataset, Page 1 of 1

< Previous page | Next page > /docserver/preview/fulltext/9789815313321/chapter-6-1.gif

The internet and its connectivity have revolutionized the world, enabling people to share ideas, collaborate, and assist each other across various domains. Despite its benefits, the progress of technology comes with the inherent danger of being targeted by cybercriminals, which can compromise individuals' privacy and security online. Intrusion detection systems (IDSs) are used to identify and prevent such threats. This paper presents a hybrid ensemble module that uses a diverse set of weak learners to build a robust IDS capable of detecting new attacks that signaturebased methods may miss. The research utilizes various ML techniques to develop a classification model that addresses the challenge of selecting suitable modules for IDS based on datasets. The proposed hybrid ensemble module provides an effective solution to enhance the accuracy and efficiency of IDS and mitigate the risk of cyberattacks in various fields, including healthcare, food service, and education.