Perancangan Sistem Keamanan Jaringan Menggunakan Instruction Detection System (IDS) Berbasis AI (Artificial Intelligence)

Abstrak

Perkembangan teknologi jaringan komputer yang semakin pesat seiring dengan meningkatnya ancaman serangan siber menuntut adanya sistem keamanan jaringan yang andal dan adaptif. Serangan seperti Denial of Service (DoS), malware, dan akses tidak sah dapat mengancam keamanan data serta kestabilan sistem jaringan. Penggunaan mekanisme keamanan konvensional seperti firewall dinilai belum cukup untuk mendeteksi serangan secara cepat dan akurat. Oleh karena itu, diperlukan sebuah sistem yang mampu melakukan pendeteksian intrusi secara otomatis, yaitu Intrusion Detection System (IDS). Penelitian ini bertujuan untuk mengembangkan sistem keamanan jaringan menggunakan Intrusion Detection System (IDS) berbasis Artificial Intelligence (AI). Metode penelitian yang digunakan adalah metode kuantitatif dengan pendekatan eksperimen. Data yang digunakan berasal dari dataset publik IDS, yaitu NSL-KDD dan CICIDS2017. Proses pengolahan data meliputi tahap preprocessing, pembagian data latih dan data uji, pelatihan model machine learning, serta pengujian sistem menggunakan metrik evaluasi berupa akurasi, precision, recall, dan F1-score.

Kata Kunci: Keamanan Jaringan, Intrusion Detection System, Artificial Intelligence, Machine Learning, IDS.

The rapid development of computer network technology is accompanied by an increasing number of cyber threats that require reliable and adaptive network security systems. Attacks such as Denial of Service (DoS), malware, and unauthorized access can threaten data security and network stability. Conventional security mechanisms such as firewalls are considered insufficient to detect attacks quickly and accurately. Therefore, an automatic intrusion detection system, known as an Intrusion Detection System (IDS), is needed. This study aims to develop a network security system using an Artificial Intelligence-based Intrusion Detection System (IDS). The research method used is a quantitative approach with an experimental method. The data used in this study were obtained from public IDS datasets, namely NSL-KDD and CICIDS2017. The data processing stages include preprocessing, data splitting into training and testing sets, machine learning model training, and system evalu [1]ation using performance metrics such as accuracy, precision, recall, and F1-score.

Keywords: Network Security, Intrusion Detection System, Artificial Intelligence, Machine Learning,