<![CDATA[Government data centers serve as critical infrastructure for national digital sovereignty, yet they remain highly vulnerable to sophisticated cyber threats. Recent incidents, notably the 2024 LockBit 3.0 ransomware attack on Indonesia’s Temporary National Data Center (PDNS 2), have exposed the fundamental limitations of traditional signature-based security systems. This research proposes the design of an Artificial Intelligence (AI)-powered Intrusion Detection System (IDS) specifically tailored for government data center environments. Utilizing the Knowledge Discovery in Databases (KDD) framework, the system was evaluated against the CICIDS2017 and NSL-KDD benchmark datasets. To address the challenge of imbalanced network traffic, the study implemented the Synthetic Minority Oversampling Technique (SMOTE) combined with Edited Nearest Neighbors (ENN). Experimental results demonstrate that the Random Forest (RF) and XGBoost algorithms achieve superior performance, reaching an overall accuracy of 99.66%. While RF excels in recall for detecting Distributed Denial of Service (DDoS) and Brute Force attacks, Support Vector Machine (SVM) provides higher precision in minimizing false positives. Additionally, deep learning models such as LSTM show effectiveness in identifying complex temporal patterns like botnets. The integration of this AI-IDS into the National Data Center (PDN) architecture not only aligns with the Personal Data Protection Law (UU PDP) of 2022 but also fulfills the audit standards mandated by BSSN Regulation No. 8 of 2024. This study concludes that an autonomous, AI-driven defense mechanism is essential to ensuring proactive security and service continuity within the Indonesian government’s digital ecosystem]]>
Copyrights © 2026
