Skripsi

SISTEM DETEKSI SERANGAN SIBER PADA JARINGAN SCADA PROTOKOL IEC 60870-5-104 MENGGUNAKAN PENDEKATAN MACHINE LEARNING

---

Penilaian

---

Supervisory and Data Acquisition (SCADA) plays an important role in industry by providing process automation, centralized control and monitoring processes. SCADA is designed for closed areas with special protocols that are isolated from the internet, but modern SCADA systems are required to be connected to one or more other network protocols to make it easier to access the SCADA system from heterogeneous networks, thus increasing vulnerability in this system. This phenomenon is interesting to study because there are still few researchers conducting a comprehensive discussion of security on the SCADA network, besides the performance of open source IDS (Intrusion Detection System) such as Snort and Suricata is less efficient in detecting disturbances on the SCADA network so that this research has the aim of designing an ideal IDS for SCADA networks using a machine learning approach. To produce an IDS that is able to work well to detect attacks in the SCADA network, a relevant dataset is needed, then the attack patterns recognition is carried out to obtain relevant features that will be used as training data for the IDS model, the selection of machine learning algorithms that are relevant to the SCADA network by paying attention to the performance of the resulting IDS model. This research has the novelty of finding attack patterns on the IEC 60870-5-104 protocol. The datasets used are the dataset from maynard_2018 and the comnets_scada_iec104 dataset. The comnets_scada_iec104 dataset was created using a physical testbed close to the actual conditions of the SCADA system. The highest accuracy of the IDS model when using the maynard_2018 dataset is 98.84% with the decision tree algorithm. The highest accuracy of the IDS model using the comnets_scada_iec104 dataset was obtained using the decision tree and random forest algorithms with the same accuracy level of 99.05%. This accuracy was obtained by adding a random under-sampling method.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307004927	T126432	T1264322023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1264322023

Publisher

Indralaya : Prodi Doktor Ilmu Teknik, Bku Teknik Informatika, Fakultas Teknik, Universitas Sriwijaya., 2023

Collation

xvi, 125 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

621.390 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Teknik komputer
Sistem Pertahanan Berbasis Software
Prodi Doktor Ilmu Teknik

Specific Detail Info

-

Statement of Responsibility

PITRIA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment