Issues and Challenges in Building a Model for Intrusion Detection System
R Lalduhsaka, AK Khan, Amit Roy · 2021 5th International Conference on Information Systems and Computer Networks (ISCON) · 2021
An Intrusion Detection System (IDS) is crucial nowadays especially in an organization or industries due to the increase in the number of threats launched by attackers. The research on developing efficient IDS model has been going on for decades and many models had been developed with decent performance but have their limitations mainly on detecting zero-day attacks and false alarms. Networking attacks are of different types and each type is having different variants. A collection of data from the network traffic is needed to train the model for future investigation. The presence of various kinds of attacks and lack of appropriate datasets form a barrier to build an efficient model for the IDS. In this paper, we present a detailed investigation of various issues and challenges in the building of an IDS, mainly focusing on the application of Machine Learning (ML) in IDS.