Deteksi Ddos pada Unbalanced Dataset Menggunakan PCA dan Local Outlier Factor
Abstract
Dataset DDoS adalah salah satu data yang sering tersedia dalam bentuk tidak seimbang(Unbalanced) antara cluster data serangan dengan cluster data normal. beberapa teknik klasifikasi telah diterapkan untuk mengatasi permasalahan ini salah satunya adalah menggunakan teknik Local Outlier Factor. Tujuan dari penelitian ini adalah untuk mengevaluasi kinerja teknik LOF dalam mendeteksi paket data yang merupakan serangan DDoS.. Sebelum dataset digunakan, dilakukan pembersihan data dan seleksi fitur menggunakan PCA. Penentuan hasil secara keseluruhan menggunakan metrik F1-Score. Nilai F1-Score terendah terdapat pada pengaturan Neighbour=12 dan Contamination=0,5 sebesar 0,619205. Nilai F1-Score tertinggi terdapat pada pengaturan Neighbour=19 dan Contamination=0,1 sebesar 0,957500 .
Downloads
Authors who publish with Elsains: Jurnal Elektro agree to the following terms:
- Authors transfer the copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.. that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access)