English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

[Id] Penggunaan Intrusion Detection System (IDS) pada jaringan komputer merupakan hal yang diperlukan untuk menjaga keamanan jaringan. Beberapa IDS berbasis K-nearest neighbor (KNN) memiliki akurasi yang relatif baik namun jika data training terlalu besar, waktu yang diperlukan untuk mendeteksi serangan juga meningkat. Waktu untuk deteksi bisa ditekan dengan mereduksi search space pada data training. Namun problem reduksi search space dengan mempertahankan kualitas deteksi masih merupakan problem terbuka. Pada artikel ini diajukan suatu metode transformasi "cakar ayam" berbasis jumlah jarak data ke centroid dan jarak data ke dua sub-centroid untuk mereduksi search space pada IDS berbasis K-nearest neighbor. Localized K-nearest neighbor dilakukan pada data yang telah tertransformasi. Eksperimen menggunakan agglome-rative hierarchial clustering dengan Unweighted Pair-Group Method of Centroid pada dataset NSL-KDD 20% menunjukkan penurunan search space maksimum sebesar 38% dengan tingkat akurasi sebesar 77.5%. Tingkat akurasi dan specificity maksimum yang dicapai pada eksperimen sebesar 88% dan 88.3% dengan tingkat reduksi sebesar 12% dan tingkat sensitifity maksimum yang dicapai sebesar 80.2% pada tingkat reduksi 11%. Berdasarkan eksperimen, luas search space dapat dikurangi sambil menjaga akurasi deteksi. Rasio tradeoff antara akurasi dan search space mungkin dapat diperbaiki dengan mengganti algortima clustering dengan divisive hierarchial clustring. Abstract : clustering, deteksi intrusi, keamanan jaringan [En] Intrusion detection System (IDS) for computer network has became an essential needs to ensure network security. Some K-nearest neighbor (KNN) based IDS have a relatively good accracy in detecting attack, but the need to use all training data costs time consumption . Detection time cost can be reduced by reducing search space needed for the algorithm. The problem of search space reduction while maintaining decent accuracy still an open problem. In this Paper we propose a new transformation method "chiken claw" method. which based on sum of two distances. The first distance is the distance of data and its cluster. The later is distance of data to 2 of its cluster's sub-centroid..This method is proposed to reduce the search space on K-nearest neighbor based IDS because the search is based on resulted one dimentional transformed data. Experiment using Unweighted Pair-group Method of centroid on NSL-KDD 20% shows maximum search space reduction 38% with 75% accuracy. Maximum accuracy and sensitivity in the experiment is 88% and 88.3% respectively with space reduction 12%. Maximum sensitivity from experiment is at 80.2% with 11% space reduction. Based on experiments, search space can be reduced while maintaining accuracy. Search space-accuracy trade off might be improved by using different clustering algorithm such as divisive hierarchial clustering

METODE TRANSFORMASI CAKAR AYAM UNTUK MEREDUKSI SEARCH-SPACE PADA INTRUSION DETECTION SYSTEM BERBASIS K-NEAREST NEIGHBOR