Open AccessDeteksi Intrusi Pada Basis Data Menggunakan Random Forest
Author(s) -
Novianti Indah Putri,
Arief Zulianto,
Wiwin Suwarningsih
Publication year - 2021
Publication title -
jurnal ict : information communication and technology/jurnal ict (information communication and technology)
Language(s) - English
Resource type - Journals
eISSN - 2303-3363
pISSN - 2302-0261
DOI - 10.36054/jict-ikmi.v20i2.424
Subject(s) - computer science , random forest , database transaction , database , intrusion detection system , data mining , hacker , intrusion , value (mathematics) , network security , field (mathematics) , computer security , artificial intelligence , machine learning , mathematics , geochemistry , pure mathematics , geology
More services have been made online in recent years, more and more data is being stored virtually. This important and confidential data becomes an easy target for criminals in the era of digitalization. Database security becomes very necessary to keep data safe. Attacks can come from outside or from within, attacks caused by insiders are the second biggest threat after hacking. Conventional security has not been able to detect anomalies from internal users. This can be anticipated using an intrusion detection mechanism. This mechanism has previously been applied to networks and hosts. However, some actions that are harmful to the database are not necessarily harmful to the network and hosts so that intrusion detection on the database becomes extra security to defend the database from intruders. This system uses the Random Forest algorithm which includes supervised learning to detect anomalous transactions. The dataset used is a transaction log containing 773 records and 9 attributes. Anomalies are determined based on the threshold value of 3 attributes, namely operation, object and field name. The test uses 6 different trees, 10, 20, 40, 60, 80 and 100. The results of the test on 762 records and 5 attributes used, the Random Forest algorithm has the highest accuracy value on the number of trees 80 and 100 which have a test time difference of 0 .03 seconds. In the dataset used, the optimum number of trees is found at number 80 with an accuracy value of 99.56% and an execution time of 0.13183 seconds.