Enhancing Linux System Security Anomaly Detection and Kernel Level Mitigation of Cyber Threats

View at publisher Summarise with VIRAT
Authors: S. Premkumar, Edwin Shalom Soji
Cited by: 0
References: 30

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Sophisticated cyber attackers are increasingly targeting Linux-based systems, so developers must implement advanced security features that detect abnormal behavior and protect the systems effectively. Signature-based detection systems often fail to detect new security threats and kernel-level intrusions due to limitations in traditional intrusion detection techniques. An AI-driven anomaly detection framework that integrates with live kernel-level protection methods addresses existing limitations. The system implements deep learning-based modeling to analyze authentic Linux attack datasets, achieving a detection precision of 92.4% while its false positive rate declines to 45.3%. Real-time protection becomes possible through the proposed method because it shortens response times by 89.6%. Tests conducted through the Linux infrastructure on the cloud show that the proposed solution results in fewer system failures compared to current protection options.

Fields of Study & Subjects

Network Security and Intrusion Detection Security and Verification in Computing Advanced Malware Detection Techniques

Publication details

Journal / source
IGI Global eBooks
Pages
269–296
Publication date
19 March 2026
Language
NG
Document type
Book chapter