Repositori Institusi

Politeknik Siber dan Sandi Negara

  • Home
  • Information
  • News
  • Help
  • Librarian
  • Member Area
  • Select Language :
    Arabic Bengali Brazilian Portuguese English Espanol German Indonesian Japanese Malay Persian Russian Thai Turkish Urdu

Search by :

ALL Author Subject ISBN/ISSN Advanced Search

Last search:

{{tmpObj[k].text}}
Image of Implementasi sistem multi Intrusion Detection System (IDS) dan algoritma Support Vector Machine (SVM) pada Machine Learning (ML) untuk mendeteksi serangan DoS attack dan probe attack
Bookmark Share

Text

Implementasi sistem multi Intrusion Detection System (IDS) dan algoritma Support Vector Machine (SVM) pada Machine Learning (ML) untuk mendeteksi serangan DoS attack dan probe attack

Achmad Husein Noor Faizi - Personal Name; Amiruddin - Personal Name; Raden Budiarto Hadiprakoso - Personal Name; Dimas Febriyan Priambodo - Personal Name;

Meningkatnya kejahatan dan serangan siber menjadikan keamanan jaringan sebagai prasyarat dasar bagi organisasi, tetapi organisasi tidak bisa menjamin hal tersebut karena penggunaan Intrusion Detection System (IDS) pada suatu organisasi masih menggunakan IDS bersensor tunggal, baik hanya berupa Host-Based IDS (HIDS) maupun hanya berupa Network-Based IDS (NIDS). Batasan ruang lingkup deteksi keduanya mengakibatkan kurangnya jumlah intrusi yang terdeteksi dari IDS yang ingin digunakan, oleh karena itu peneliti mengintegrasikan NIDS dan HIDS untuk dijadikan multi-IDS guna menyatukan ruang lingkup keduanya untuk memperbanyak intrusi yang mampu terdeteksi dari sistem mitigasi serangan yang akan dibangun.

Namun, tingginya nilai False Positive dan False Negative pada NIDS dan HIDS menjadi sebuah permasalahan tersendiri Ketika keduanya diintegrasikan. Oleh karena itu, peneliti menggunakan machine learning untuk meningkatan akurasi deteksi terhadap data serangan yang masuk. Hasil penelitian menunjukkan machine learning yang digunakan untuk melakukan analisis statis terhadap dataset NSL-KDD mencapai 99% untuk serangan bertipe DoS attack dan 98% untuk serangan bertipe Probe attack. Langkah selanjutnya yaitu analisis secara dinamis terhadap simulasi serangan yang dilakukan secara realtime menghasilkan plugin machine learning mampu mendeteksi secara penuh serangan bertipe DoS attack dan plugin machine learning mampu mendeteksi lebih detil adanya kemungkinan serangan SYN Flooding DoS attack melalui paket serangan Probe attack dibanding dengan ruleset community rules milik Snort. --

The increase in cybercrime and cyber-attacks makes network security a basic prerequisite for organizations, but organizations cannot guarantee this because the use of an Intrusion Detection System (IDS) in an organization still uses a single sensor IDS, either only in the form of Host-Based IDS (HIDS) or only in the form of Network-Based IDS (NIDS). The limitation of the detection scope of the two results in a lack of intrusion detected from a single IDS system, therefore the researcher integrates NIDS and HIDS to become multi-IDS to unify the scope of the two to increase the intrusion that can be detected from the attack mitigation system that will be built.

However, the high value of False Positive and False Negative on NIDS and HIDS becomes a problem in itself when the two are integrated. Therefore, researchers use machine learning to improve the detection accuracy of incoming attack data. The results showed that the machine learning used to perform static analysis of the NSL-KDD dataset reached 99% for DoS attacks and 98% for Probe attacks. Meanwhile, for dynamic analysis of attack simulations carried out in real-time, machine learning plugins can fully detect DoS attack types and machine learning plugins can detect in more detail the possibility of SYN Flooding DoS attacks through Probe attack packages compared to the Snort community rules set.


Availability

No copy data

Detail Information
Series Title
-
Call Number
2022 ACH i
Publisher
Bogor : Poltek SSN., 2022
Collation
xiv, 59 hlm.
Language
Indonesia
ISBN/ISSN
--
Classification
--
Content Type
-
Media Type
-
Carrier Type
-
Edition
--
Subject(s)
Artificial Intelligence
Computer security
Data sets
DoS attacks
HIDS
Multi-IDS
NIDS
Probe attacks
Specific Detail Info
-
Statement of Responsibility
Achmad Husein Noor Faizi
Other version/related

No other version available

File Attachment
No Data
Comments

You must be logged in to post a comment

Repositori Institusi
  • Information
  • Services
  • Librarian
  • Member Area

About Us

Search

start it by typing one or more keywords for title, author or subject

Keep SLiMS Alive Want to Contribute?

© 2025 — Senayan Developer Community

Powered by SLiMS
Select the topic you are interested in
  • Computer Science, Information & General Works
  • Philosophy & Psychology
  • Religion
  • Social Sciences
  • Language
  • Pure Science
  • Applied Sciences
  • Art & Recreation
  • Literature
  • History & Geography
Icons made by Freepik from www.flaticon.com
Advanced Search
Where do you want to share?