Claim Missing Document
Check
Articles

Found 29 Documents
Search

XGBoost-Powered Ransomware Detection: A Gradient-Based Machine Learning Approach for Robust Performance Ghozi, Wildanil; Lestiawan, Heru; Sani, Ramadhan Rakhmat; Hussein, Jassim Nadheer; Rafrastara, Fauzi Adi
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 4, November 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i4.2405

Abstract

Ransomware remains a rapidly evolving cyber threat, causing substantial financial and operational disruptions globally. Traditional signature-based detection systems are ineffective against sophisticated, zero-day attacks due to their static nature. Consequently, machine learning-based approaches offer a more effective and adaptive alternative. This study proposes an approach utilizing XGBoost for highly effective ransomware detection. We conducted a rigorous comparative analysis of prominent ensemble learning algorithms—XGBoost, Random Forest, Gradient Boosting, and AdaBoost—on the RISS Ransomware Dataset, comprising 1,524 instances. Our experimental results unequivocally demonstrate XGBoost as the superior ensemble model, achieving an impressive 97.60% accuracy and F1-Score. This performance surpassed Gradient Boosting (97.20%), Random Forest (96.94%), and AdaBoost (96.50%). Furthermore, this study benchmarked XGBoost against established state-of-the-art (SOTA) methods, including Support Vector Machine (SVM) and the SA-CNN-IS deep learning approach. The comprehensive results underscore the core contribution of this study: by applying XGBoost with a carefully structured machine learning pipeline, our approach consistently outperforms two state-of-the-art methods (SVM and SA-CNN-IS) as well as other ensemble algorithms. This highlights the critical role of methodological precision in maximizing detection performance against evolving ransomware threats.
Mitigating Class Imbalance in DDoS Detection: The Impact of Random Over Sampling on Machine Learning Performance Ghozi, Wildanil; Hussein, Jasim Nadheer; Sani, Ramadhan Rakhmat; Rafrastara, Fauzi Adi; Paramita, Cinantya; Supriyanto, Catur
ELKHA : Jurnal Teknik Elektro Vol. 17 No.2 October 2025
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v17i2.95037

Abstract

Distributed Denial of Service (DDoS) attacks are a major cybersecurity threat, involving malicious traffic generated from numerous compromised sources to overwhelm and disable targeted services. Although machine learning (ML) has shown promise in detecting DDoS attacks through network traffic analysis, a key challenge remains: the class imbalance in datasets such as UNSW-NB15, where normal traffic significantly outweighs attack instances. This imbalance leads to biased predictions and degraded detection performance for minority attack classes. To address this issue, our study investigates the impact of Random Over Sampling (ROS), a simple yet effective balancing technique on improving detection accuracy in multi-class DDoS classification tasks. While prior works have primarily focused on ensemble algorithms or feature selection, our approach is distinct in emphasizing the effect of data balancing on macro evaluation metrics such as macro precision, macro recall, and macro F1-score. ROS was selected over more complex alternatives, such as SMOTE or ADASYN, due to its computational efficiency and ability to establish a performance baseline without introducing synthetic noise. We evaluate four machine learning algorithms: Decision Tree, Naïve Bayes, Random Forest, and XGBoost, using the UNSW-NB15 dataset. The results show that Decision Tree combined with ROS yields the highest improvement in macro F1-score, increasing by 36%. However, this improvement is accompanied by a moderate reduction in accuracy for certain algorithms. These findings highlight the critical role of class balancing in enhancing the reliability of DDoS detection models, especially in imbalanced multi-class scenarios.
Implementasi Website BumDes Manggala Karsa Desa Karangsari, Kec. Pejawaran, Kab. Banjarnegara Setiono, Oki; Salam, Abdus; Ghozi, Wildanil; Handoko, L. Budi
Jurnal Pengabdian kepada Masyarakat Nusantara Vol. 4 No. 4 (2023): Jurnal Pengabdian kepada Masyarakat Nusantara (JPkMN)
Publisher : Lembaga Dongan Dosen

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

Abstract

Desa Karangsari, Pejawaran, Banjarnegara belum memiliki website untuk BUMDes yang digunakan sebagai sarana informasi kegiatan dan promosi hasil produk UMKM desa. Kegiatan BUMDes belum terdokumentasi dengan baik, layanan kepada masyarakat untuk kegiatan BUMDes belum menggunakan teknologi informasi serta informasi produk dan jasa yang dikelola BUMDes belum tersebar dengan maksimal.Tujuan yang hendak dicapai adalah pendampingan pengembangan website BUMDes desa Karangsari, Kec. Pejawaran, Kab. Banjarnegara untuk meningkatkan kinerja dan layanan BUMDes kepada masyarakat. Hasil yang dicapai berupa website BUMDes untuk layanan publik dan mengenalkan unit usaha serta penjualan produk UMKM desa
Prediksi Potensi Kinerja Calon Karyawan Customer Service Call Center Menggunakan Model Machine Learning Berbasis Data Rekrutmen Pratama, Andriyan Yoga; Ghozi, Wildanil
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7285

Abstract

Employee selection process is a critical stage for companies in acquiring high-quality human resources (HR), particularly for customer service call center positions that demand excellent communication skills and strong work endurance. Data-driven recruitment methods have demonstrated improved accuracy compared to traditional, often subjective, approaches. This study aims to develop a predictive model to assess the potential performance of candidates during the HR interview stage, based on educational background, work experience, and other relevant factors, using machine learning algorithms. The dataset utilized includes demographic information, education levels, previous work experience, and other factors that may influence candidate performance in customer service roles. The models tested in this study include Decision Tree, Random Forest, and Artificial Neural Network algorithms. The analysis shows that GPA, prior work experience, and organizational involvement significantly correlate with the potential performance of candidates. The application of machine learning in the recruitment process can enhance selection effectiveness and improve HR efficiency. Through this approach, companies are expected to make more accurate hiring decisions and select the best candidates with greater precision.
Analisis Tripartit Keamanan Docker: Evaluasi Metode Deteksi Kerentanan, Registry, dan Layanan Widyanto Utomo, Arya; Ghozi, Wildanil; Umam, Chaerul
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2983

Abstract

The adoption of Docker as the standard container platform poses new security challenges, particularly regarding vulnerabilities in public images. This study evaluates the effectiveness of three vulnerability scanning methods for Docker images: direct scanning, vendor-integrated SBOM scanning, and cross-vendor SBOM scanning, using Trivy and Grype on 36 images from three major registries (Docker Official, Bitnami, Chainguard). The results show that direct scanning and vendor-integrated SBOM scanning produce identical detections (12,023 vulnerabilities with Trivy; 8,950 with Grype), while cross-vendor SBOM scanning decreases dramatically by more than 90% (only 800–790 findings). Chainguard proved to be the most secure, while Docker Official was the most vulnerable (e.g., python:latest had 2,053 vulnerabilities). Programming language-based images (Rust: 3,825; Node.js: 3,816) were also riskier than specialized services (Redis: 341; MongoDB: 351). This research developed a framework for evaluating the effectiveness of cross-approach vulnerability scanning and strengthened the theory of software supply chain security through the concept of SBOM provenance dependency, which became the basis for the development of a multi-phase vulnerability scanning framework and recommendations for secure container implementation.
Optimizing URL-Based Phishing Detection Using XGBoost and Relief Feature Selection Tyas, Wahyu Suryaning; Rafrastara, Fauzi Adi; Ghozi, Wildanil
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15651

Abstract

Phishing is a significant cybersecurity threat in which attackers exploit manipulated URLs to deceive users and obtain confidential information. As phishing attacks continue to grow in complexity, automated machine learning based detection methods have become essential to strengthen digital security. This study proposes a URL based phishing detection model using boosting algorithms while analyzing the role of feature selection in improving classification performance and computational efficiency. The experiments were conducted on a dataset consisting of 10000 instances with 50 features and balanced class labels. After data preparation, 48 features were retained as input variables, and min max normalization was applied to ensure uniform feature scaling. Three boosting algorithms namely Gradient Boosting, XGBoost, and AdaBoost were evaluated using accuracy, precision, recall, and F1 score. Among these methods, XGBoost achieved the highest accuracy of 98.8 percent, demonstrating its effectiveness in learning complex URL patterns. Subsequently, three feature selection techniques namely Information Gain, Chi Square, and ReliefF were applied and evaluated using 10 fold cross validation. The results indicate that ReliefF provides the most effective feature reduction by selecting 37 features while maintaining the same classification accuracy. Unlike previous studies that mainly focus on classifier comparison, this study demonstrates that integrating XGBoost with ReliefF enables significant feature dimensionality reduction without compromising predictive accuracy. This finding highlights an efficient trade off between detection performance and computational complexity. Overall, the proposed framework offers a robust, efficient, and scalable solution for fast and adaptive phishing detection in modern cybersecurity environments.
A Comparative Analysis of P-Value and Mutual Information Feature Selection Methods for Random Forest-Based Phishing Detection Adi Nugroho, Fahmi Bahtiar; Ghozi, Wildanil; Adi Rafrastara, Fauzi
Jurnal Nasional Teknologi dan Sistem Informasi Vol 11 No 3 (2025): Desember 2025
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v11i3.2025.377-386

Abstract

The application of ANOVA's P-Value-based feature selection method, namely the F-test, in phishing detection with the Random Forest algorithm indicates that a configuration of 25 features yields the quickest inference time, rendering it appropriate for scenarios demanding great computational efficiency and responsiveness. However, if the user's primary priority is to achieve the highest level of detection accuracy, the 29-feature configuration is more feasible because it exhibits higher accuracy performance and better prediction stability. Consequently, there is no definitive trade-off between 25 or 29 features, there exists a selection of solutions that can be tailored to the application's requirements. This methodology enables users to achieve an optimal equilibrium between superior performance and minimal inference time in a phishing detection system, contingent upon the implementation context and operational priorities. This study successfully shows that a simple statistical approach such as P-Value is not only competitive but also provides superior results compared to more complex methods, offering a practical and efficient solution for real-world implementation.
Trends in Interpretable and Lightweight Intrusion Detection Systems: A Bibliometric Analysis of Network Traffic Anomaly Detection Pramudya, Elkaf; Hafsarah Maharrani, Ratih; Abdussalam, Abdussalam; Ghozi, Wildanil
Infotekmesin Vol 17 No 1 (2026): Infotekmesin: Januari 2026
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v17i1.3093

Abstract

This study examines recent developments in interpretable and lightweight Intrusion Detection Systems (IDS) through a bibliometric analysis of 399 publications on network traffic anomaly detection from 2019 to 2025. Using a structured workflow comprising data collection, filtering, topic categorization, and visualization, the analysis reveals a significant increase in IDS-related publications, rising from fewer than 20 papers per year before 2019 to over 200 in 2025, reflecting growing interest in efficient and transparent security solutions. Topic categorization identifies IDS as the dominant research area, followed by Lightweight approaches, Anomaly Detection, IoT, and Explainability, with minimal contributions from other topics. Citation patterns confirm IDS and lightweight methods as the most influential themes. Journal analysis highlights Applied Sciences, Electronics, and IEEE Access as the leading publication venues. Overall, the findings indicate a clear shift toward IDS research emphasizing low computational cost, practical deployment, and model transparency, while also underscoring the ongoing need for unified benchmarks, realistic datasets, and evaluation frameworks to support broader adoption of interpretable and lightweight IDS technologies.
Optimasi Deteksi Malware Android pada Dataset Drebin Menggunakan Ensemble Learning Usmany, Haidar Nafiis; Ghozi, Wildanil
Building of Informatics, Technology and Science (BITS) Vol 7 No 4 (2026): March 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i4.9443

Abstract

The increasing number and complexity of Android malware require detection systems that are accurate, efficient, and capable of handling high-dimensional data. Machine learning–based approaches have become one of the widely adopted solutions in cybersecurity research. However, the performance of classification models is often affected by feature redundancy and suboptimal hyperparameter configurations. This study aims to evaluate the effectiveness of combining Random Forest–based feature selection with modern boosting classification algorithms for Android malware detection. The dataset used in this study is the Drebin 215 dataset, which was selected because it is one of the most widely used benchmark datasets for Android malware detection based on static analysis, enabling more objective comparison with previous studies. Feature selection was performed using the Random Forest feature importance method to reduce data dimensionality prior to the classification stage. The classification models employed include XGBoost, Light Gradient Boosting Machine (LightGBM), and CatBoost. The experiments were conducted under two scenarios: without hyperparameter optimization (non-tuning) and with hyperparameter optimization using the Grid Search method. Model performance was evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics, as well as computational time analysis. The experimental results show that all models achieved very strong classification performance on the Drebin benchmark dataset, with accuracy values exceeding 0.98. Among the evaluated models, LightGBM achieved the best performance, with an accuracy of 0.9900 and an F1-score of 0.9865. This performance advantage is likely influenced by the efficiency of its histogram-based learning mechanism and leaf-wise tree growth strategy, which enables faster and more effective learning on high-dimensional data. Nevertheless, the high performance observed on this benchmark dataset still requires further evaluation on more diverse datasets or dynamic environments to ensure the generalization capability of the model in real-world scenarios. The findings of this study indicate that the combination of Random Forest–based feature selection and boosting algorithms can serve as an effective approach for improving the efficiency and performance of Android malware detection systems.