Skripsi
ANALISIS DATA TIME SERIES UNTUK FORECASTING DATA CYBER ATTACK PADA HONEYPOT MENGGUNAKAN METODE SUPPORT VECTOR REGRESSION (SVR).
Cyber Attack is a crime that attacks computer systems that can shut down or damage information technology services. Every act of attack will have an impact on gaining access to services, manipulating and various dangerous actions. There are various reasons why cyber attacks can occur, one of which is that there is still very little information about the predictability of cyber security. This study aims to determine and obtain the results of forecasting time series data and IP Address on honeypot using the Support Vector Regressio method and determine the Support Vector Regression (SVR) method that can produce the best forecasting in forecasting IP data and cyber attack time data on honeypot data. In this study using the Support Vector Regression (SVR) method with three kernels namely Linear, Polynomial, and Radial Basis Function (RBF). The kernel that gives the best results is based on the smallest MAE, RMSE, and MAPE values. The results of this study obtained, the assessment of the best time data forecasting results obtained using the RBF kernel function with cross validation which obtained the smallest error with MAE = 5.6904%, RMSE = 6.5858%, and MAPE = 4.7047% before data scaling, and with MAE = 0.8212%, RMSE = 0.9493%, and MAPE = 1.3199% after data scaling. While the IP data forecasting model obtained using the Polynomial kernel function MAPE = 5.2212% before data scaling and MAPE = 1.0% after data scaling. Keywords: Cyber Attack, Support Vector Regression, Kernel.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307006201 | T129899 | T1298992023 | Central Library (Referens) | Available |
No other version available