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 Deteksi Serangan Web Defacement Menggunakan Deep Learning
Bookmark Share

Text

Deteksi Serangan Web Defacement Menggunakan Deep Learning

Herman Kabetta - Personal Name; Nurul Qomariasih - Personal Name; R Budiarto Hadiprakoso - Personal Name; Shakira Putri Ayunda - Personal Name;

Abstrak:
Web defacement adalah tindakan yang dilakukan oleh seseorang atau sekelompok orang untuk mengubah tampilan atau konten sebuah situs web tanpa izin dari pemilik atau pengelola situs tersebut. Dampak dari serangan web defacement dapat berupa terganggunya operasi situs web hingga kerugian finansial bagi pemilik web tersebut. Salah satu cara untuk mendeteksi web defacement adalah dengan menggunakan deep learning. Penelitian ini menerapkan model deep learning Bi-LSTM, GRU, dan BERT dalam mendeteksi serangan web defacement. Penelitian ini dimulai dengan melakukan pengumpulan data dari sumber terbuka, berupa defaced website dan normal website. Tahap selanjutnya dilakukan penyesuaian data agar dataset dapat diolah oleh model, seperti data cleansing dan case folding. Kemudian dilakukan pemodelan dengan model yang telah dipilih. Setelah dilakukan pemodelan, dilakukan pengujian dan evaluasi dengan menggunakan confusion matrix sebagai bahan pertimbangan untuk menentukan model terbaik. Model yang memperoleh nilai confusion matrix tertinggi di antara kedua model lainnya adalah BERT dengan akurasi sebesar 0,993. Selanjutnya, model ini diimplementasikan ke dalam website yang dibangun menggunakan framework Flask.
Abstract:
Web defacement is an act carried out by an individual or a group of people to alter the appearance or content of a website without the permission of its owner or administrator. The impact of web defacement attacks can range from disrupting the website's operations to causing financial losses for the website owner. One of the methods to detect web defacement is by employing deep learning techniques. This research applies deep learning models such as Bi-LSTM, GRU, and BERT to detect web defacement attacks. The study begins by collecting data from open sources, consisting of both defaced and normal websites. The next step involves data preprocessing to make the dataset suitable for model training, including data cleansing and case folding. Subsequently, the models are developed and trained using the chosen deep learning techniques. After modeling, testing and evaluation are conducted, utilizing the confusion matrix as a basis for determining the best-performing model. BERT achieved the highest confusion matrix score among the models, with an accuracy of 0.993. Consequently, this model is implemented into a website built using the Flask framework.


Availability

No copy data

Detail Information
Series Title
--
Call Number
2023 SHA d
Publisher
Bogor : Politeknik Siber dan Sandi Negara., 2023
Collation
xii, 28 halaman
Language
Indonesia
ISBN/ISSN
--
Classification
Rekayasa Perangkat Lunak Kriptografi
Content Type
-
Media Type
-
Carrier Type
-
Edition
--
Subject(s)
deep learning
GRU
web defacement
Bi-LSTM
BERT
Specific Detail Info
-
Statement of Responsibility
Shakira Putri Ayunda
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?