UK-IDS-Machine Learning Based Intrusion Detection System for Unknown Attack Detection

Title

UK-IDS-Machine Learning Based Intrusion Detection System for Unknown Attack Detection

Creator

Sowmya, T.; Mary Anita, E.A.; Lapina, Maria

Description

Computer networks have become the major focus for attackers. Hence intrusion detection system plays a significant role in detecting attacks. Many researchers have already focused on the domain of cyber security by developing an efficient framework. However, developing an efficient IDS is still a challenging task because of its effectiveness in determining novel attacks. Hence in the current study, a machine learning based IDS called UK-IDS is proposed by incorporating OC-SVM and a basic SVM model. The aim of the proposed system is to achieve high accuracy and F1 score by detecting novel attacks. The OC-SVM approach identifies the novel attacks by collaborating the clustering and thresholding mechanism. The basic SVM model is to distinguish the type of attack. The experimental study reveals that UK-IDS framework shows good performance in terms of accuracy and F1 score. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Source

Lecture Notes in Networks and Systems;Volume;1456 LNNS;pp.425-433

Date

01-01-2026

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

Artificial Intelligence (AI); Intrusion Detection System(IDS); One Class SVM(OC-SVM); Unknown -Intrusion Detection System(UK-IDS)

Coverage

Sowmya T., Christ University, Bangalore, India; Mary Anita E.A., Christ University, Bangalore, India; Lapina M., North Caucasus Federal University, Stavropol, Russian Federation

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 23673370; ISBN: 978-303207274-0;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-3-032-07275-7_38

https://www.scopus.com/pages/publications/105023155002?origin=resultslist