Skripsi
DETEKSI SERANGAN DENIAL OF SERVICE (DOS) PADA JARINGAN IEC 61850 SUPERVISORY CONTROL AND DATA ACQUISITION (SCADA) MENGGUNAKAN METODE LONG SHORT-TERM MEMORY (LSTM).
Supervisory Control and Data Acquisition (SCADA) is widely used in industry as a system that is tasked with supervising, controlling while simultaneously collecting data from sensors connected during the production process. SCADA has an IEC 61850 GOOSE protocol which is used as a communication line between Intelligent Electronic Device (IED). This communication line can be injected to send packets that have an abnormal status number (StNum) on a large amount and in a short period of time to carry out a Denial of Service (DoS) attack which results in the IED not being able to function properly. This research uses the Long Short-Term Memory (LSTM) algorithm to detect DoS attack patterns in the dataset. The dataset used is from IEC61850SecurityDataset which contains GOOSE protocol data on SCADA networks that have been injected with DoS. Due to the unbalanced data distribution the dataset was balanced using random oversampling. The best model from this study achieved an accuracy rate of 98.24%, with precision 100%, recall 92.22%, and F1 score 98.22%
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407003620 | T145964 | T1459642024 | Central Library (REFERENCES) | Available but not for loan - Not for Loan |
No other version available