Text
OPTIMALISASI ALGORITMA LSTM PADA SISTEM PENDETEKSI SERANGAN BRUTEFORCE MENGGUNAKAN METODE BIDIRECTIONAL LSTM (BI-LSTM)
Bruteforce attack is a form of attack to be able to enter network services by making various pairs of usernames and passwords illegally. To avoid this attack you can use different character combinations such as alphabetic, alphanumeric, and alphanumeric with symbols. In an effort to protect network security systems against Bruteforce attacks, an attack detection system such as an Intrusion Detection System is needed. IDS is one of the detectors that can investigate activities that occur on internet systems and networks. The method used in this research is Bidirectional Long Short Term Memory (Bi-LSTM). In the Bi-LSTM method there is a structure that is different from a single LSTM, where Bi-LSTM can calculate input data sequentially and also in reverse order with the aim of obtaining two different external states (two directions). Besides that, the Bi-LSTM method also has a function to find out remote contextual dependencies. This study uses two types of attacks, namely FTP and SSH Bruteforce attacks taken from the CIC-IDS 2018 dataset. By validating training and testing data from 20% to 80%. As the output of this study, the best performance scores were Accuracy of 99.9923%, Recall of 99.9997%, Specificity of 99.9815%, Precision of 99.9900%, F1-Score of 99.9849%, and performance values of BACC of 99.9906% and MCC of 99.9848%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307002531 | T114178 | T1141782023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available