Claim Missing Document
Check
Articles

Found 2 Documents
Search

Evaluasi Efektivitas Firewall Pre-filtering berbasis eBPF/XDP menggunakan Random Forest untuk Deteksi Anomali Trafik pada Docker Swarm Ahmad Rohliyanto; Ema Utami
JURIKOM (Jurnal Riset Komputer) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9618

Abstract

Overlay networks in container orchestration platforms such as Docker Swarm are vulnerable to volumetric DDoS attacks, while conventional firewall solutions impose high overhead when processing large attack volumes. This paper presents the implementation and evaluation of an eBPF/XDP-based pre-filtering firewall that integrates detection rules derived from a Random Forest model to identify traffic anomalies in Docker Swarm overlay networks. Unlike previous studies that employ a single Decision Tree or process classification in user-space, this research extracts Random Forest rules into per-source-IP thresholds executed directly in the kernel via XDP and stored in an eBPF config_map to enable runtime updates without recompilation. The model was trained on the CIC-DDoS-2019 dataset (174,221 records, 65 features), achieving 99.88% accuracy, 99.90% detection rate, 0.14% false positive rate, and ROC-AUC of 0.9999. Experimental evaluation across seven testing scenarios with 10 iterations demonstrates that the XDP firewall drops over 99.9% of attack packets with a median response time of 0.69 ms, comparable to baseline conditions. CPU overhead remains low (0.92–1.18%) and throughput is maintained at approximately 920 Mbps. Differences between scenarios are statistically significant (p < 0.05) but with negligible practical effect (d < 0.25). Comparative analysis with iptables, both global rate limiting and per-IP hashlimit, indicates that all three approaches (XDP, global iptables, and per-IP iptables) effectively mitigate DDoS with comparable median response times.
Pengembangan Machine Learning dalam Preskripsi Obat Pasien untuk Mengurangi Kesalahan Penggunaan Obat dan Mencegah Kerugian Rumah Sakit akibat Pemakaian Obat yang Tidak Tepat Muh Ikbal Sodikin; Ema Utami
sudo Jurnal Teknik Informatika Vol. 4 No. 2 (2025): Edisi Juni
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/sudo.v4i2.819

Abstract

Prescribing medications to patients with chronic diseases or complications such as diabetes and stroke requires special attention, especially when patients are co-treated by an internist and a neurologist. The risk of polypharmacy and inappropriate drug administration can adversely affect patient health. This study uses the Support Vector Machine (SVM) algorithm to classify and analyze drug administration patterns in patients with chronic diseases or complications. The data used includes patient medication history, diagnosis, and prescriptions from various specialists. The SVM algorithm was implemented to identify potential overlaps or similarities in drug administration. The results of the analysis using SVM successfully identified drug administration patterns that could potentially lead to polypharmacy. The model was able to detect the similarity of drug content with 92% accuracy. The results showed that 15% of the total prescriptions analyzed had the potential for overlapping drug content. The use of the SVM algorithm in the analysis of drug prescribing proved effective in reducing the risk of polypharmacy and inappropriate drug administration in patients with chronic diseases or complications. The implementation of this machine learning-based system can help doctors make more informed prescribing decisions, improve patient safety, and optimize treatment outcomes.