Claim Missing Document
Check
Articles

The Use of PFSense and Suricata as a Network Security Attack Detection and Prevention Tool on Web servers Sufardy, Devander Benaryanta; Widiasari, Indrastanti Ratna
INOVTEK Polbeng - Seri Informatika Vol. 9 No. 2 (2024): November
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/shxy2045

Abstract

This research explores the effectiveness of PFSense and Suricata integration in detecting and preventing network security attacks on web servers. The experimental method was conducted by testing the performance of these two open-source tools in the face of four types of attacks: Ping of Death, SYN Flood, SQL Injection, and Brute Force Attack on SSH. The tests were conducted in an environment with hardware specifications such as [specify specifications, e.g. CPU, RAM, and device type], and software including [specify operating system and version of PFSense and Suricata]. The results showed that Suricata was able to detect threats with an accuracy rate of 92% and successfully blocked 85% of the attacks. The average response time of the system to detect attacks was 250 ms. The integration between PFSense and Suricata proved effective in identifying attack patterns and preventing further potential damage. With proper configuration, this combination not only keeps the web server network secure, but also provides a quick response to complex cyber threats. This research contributes to the development of more reliable network security solutions by demonstrating how the integration of PFSense and Suricata can be effectively used to protect web servers. The findings provide practical guidance for practitioners and academics in implementing more innovative approaches to enhance network security in the digital era.
Implementation of an IoT Based Billing System to Optimize Management of Billiard Table Usage Rezky Kristian Bangun; Indrastanti Ratna Widiasari
INOVTEK Polbeng - Seri Informatika Vol. 9 No. 2 (2024): November
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/v0kqfm37

Abstract

This research develops an IoT-based billing system for managing billiard table usage, aimed at addressing various issues arising from the use of manual systems. Currently, many billiard table rental businesses still rely on manual methods for transaction recording and lamp control, which increases the risk of rate manipulation, inaccurate transaction reports, and inefficient resource management. The manual process also adds to the workload of operators, especially when billiard tables are located far apart. The developed system utilizes Bluetooth sensors and a web app to automatically control the billiard table lamps, thereby reducing manipulation and improving operational efficiency. Testing shows that the system accurately calculates the usage fees and controls the lamp status based on commands from the web server. As a result, the system not only enhances the accuracy of cost calculation and the reliability of billiard table management but also provides a better user experience. Thus, the implementation of this IoT-based billing system offers significant benefits in optimizing billiard center management.
Design and Implementation of Load Balancing for Quality of Service Improvement Widiasari, Indrastanti Ratna; Efendi, Rissal
Jurnal Buana Informatika Vol. 15 No. 2 (2024): Jurnal Buana Informatika, Volume 15, Nomor 02, Oktober 2024
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

At the Information Technology Faculty, Satya Wacana Christian University, load balancing systems are implemented where the web server serves 500 users. This is to prevent server overload or downtime during simultaneous access to the web server. Test results indicate significant differences in CPU usage, request time, and bandwidth between load balancing and single servers. The use of load balancing is more effective than relying on a single server, as evidenced by test results. The CPU usage with load balancing is significantly lower, with a difference of up to 45% compared to a single server. The request time with load balancing is also slightly better, with only 21.5ms compared to 42ms for a single server. However, the difference in bandwidth between load balancing and a single server is not very significant. The highest bandwidth recorded on a single server is 182kb/s, while with load balancing it reaches 165kb/s.
Optimizing a Hybrid Deep Learning Model for DDoS Detection Using DBSCAN and PSO Widiasari, Indrastanti Ratna; Efendi, Rissal
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 6 (2025): December 2025 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i6.6383

Abstract

This study proposes a hybrid deep learning approach that combines Gated Recurrent Units (GRUs) and Convolutional Neural Networks (CNNs) for Distributed Denial of Service (DDoS) cyberattack detection. The model, called DBSCAN–GRU–CNN, uses density-based clustering (DBSCAN) to select relevant features and reduce execution time. The dataset for this study was obtained from live penetration testing, where a series of simulated attacks was performed on a monitored network. To evaluate the performance of the proposed model, several comparison models were used, including DBSCAN–GRU–CNN (Single Hidden Layer), DBSCAN–GRU–CNN (Double Hidden Layers), DBSCAN–GRU–CNN (With Regularization), DBSCAN–GRU–CNN–PSO, GRU–CNN, GRU–CNN (With Hyperparameter Tuning), and Random Forest (Tuned Model). Variations of the model tested were made by adding hidden layers, regularization, optimization with Particle Swarm Optimization (PSO), and hyperparameter tuning. Experimental results show that the DBSCAN–GRU–CNN–PSO model provided optimal performance with a 99.3% accuracy, a 99% precision, a 98.9% recall, and a 99% F1-score, while the model with hyperparameter tuning achieved a 99% accuracy. By adding PSO, the model achieved optimized weights, better generalization, and excellent accuracy in DDoS detection.