Text

DETEKSI SERANGAN DDOS DENGAN INTRUSION DETECTION SYSTEM MENGGUNAKAN METODE BIDIRECTIONAL RNN

---

Penilaian

---

DDoS attacks can cause targeted servers to become slow and web server services unavailable, but DDoS attacks are difficult to detect in a network because their traffic patterns are similar to those of legitimate clients, because attackers emulate their attack traffic among legitimate traffic to hide their attacks. In this study, datasets originating from CSE-CIC-IDS 2018 were used. There are three objectives in this study. The first is the implementation of the Corelation-based Feature Selection (CFS) feature in order to obtain important features during the attack detection process. The second is the application of the Bidirectional RNN method to detect DDoS attacks. The third is knowing the results of DDoS attack detection performance seen from the results of the values for accuracy, precision, sensitivity, specificity, F1-Score, BAAC and MMC. The deep learning method used is Bidirectional RNN, which is a branch of RNN which can duplicate the RNN processing chain so that the input can be processed in the order of the backward layer and the forward layer so that it is possible to provide an increase in high accuracy results. This research has three benefits, the first is providing optimization in terms of computation time, the second is applying the Bidirectional RNN method to detect DDoS attacks, and the third is providing the best performance when the detection process is using the Bidirectional RNN method. This research was conducted by training the CSE-CIC-IDS 2018 dataset on machine learning by tuning hyper parameters and comparing the ratios of different training data and test data so as to produce the best evaluation value with an accuracy value of 99.9954%, 99.9905% recall, 100% specificity, 100% precision, F1-Score 99.9954%, and performance BACC 99.9954%, and MCC 99.9908%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307000116	T85572	T855722022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T855722022

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer., 2022

Collation

xv, 99 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Jurusan Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment