Visible to the public Improving Accuracy for Intrusion Detection Through Layered Approach Using Support Vector Machine with Feature Reduction

TitleImproving Accuracy for Intrusion Detection Through Layered Approach Using Support Vector Machine with Feature Reduction
Publication TypeConference Paper
Year of Publication2016
AuthorsNema, Aditi, Tiwari, Basant, Tiwari, Vivek
Conference NameProceedings of the ACM Symposium on Women in Research 2016
PublisherACM
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-4278-0
Keywordsgenetic algorithm, Human Behavior, Metrics, NSL KDD dataset, pubcrawl, support vector machine, Support vector machines, threat vectors
Abstract

Digital information security is the field of information technology which deal with all about identification and protection of information. Whereas, identification of the threat of any Intrusion Detection System (IDS) in the most challenging phase. Threat detection become most promising because rest of the IDS system phase depends on the solely on "what is identified". In this view, a multilayered framework has been discussed which handles the underlying features for the identification of various attack (DoS, R2L, U2R, Probe). The experiments validates the use SVM with genetic approach is efficient.

URLhttp://doi.acm.org/10.1145/2909067.2909100
DOI10.1145/2909067.2909100
Citation Keynema_improving_2016