Claim Missing Document
Check
Articles

Found 32 Documents
Search

Detection of SQL Injection, XSS, and Command Injection Attacks in Web Payloads Using SVM, Random Forest, and XGBoost Andrian Eko Widodo; Fabriyan Fandi Dwi Imaniawan
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1655

Abstract

Web application attacks, including SQL Injection (SQLi), Cross-Site Scripting (XSS), and Command Injection (CmdI), remain major threats to digital services. This study develops and evaluates an adversarial-aware protocol for multi-class malicious payload detection, focusing on accuracy, robustness against non-adaptive mutations, and practical inference feasibility. The protocol compares LinearSVC, Random Forest, and XGBoost with character-level neural baselines, namely character CNN and BiLSTM, and a transparent rule-based comparator. Evaluation integrates stratified sampling, deduplicated validation, mutation testing, SHAP-based interpretation, and end-to-end throughput measurement. Experiments used 49,998 stratified records from the SQLi-XSS-CommandInjection dataset in Google Colaboratory. On the internal test set, XGBoost obtained the best performance, achieving 99.28% accuracy and 99.32% macro F1-score. After removing 878 exact duplicate records for stricter re-evaluation, XGBoost maintained 99.21% accuracy and 99.24% macro F1-score, indicating that the findings were not driven solely by duplicate leakage. The complete preprocessing, feature extraction, and prediction pipeline reached an average CPU inference time of 0.832 ms per sample. SHAP analysis of Random Forest highlighted injection operators, script fragments, keyword hits, and structural tokens as discriminative features. The results provide a controlled benchmark, although validation on real HTTP logs remains future work.
ANALISIS SENTIMEN MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR PADA REVIEW APLIKASI SHOPEE Fanny Fatma Wati; Nadiyah Hidayati; Mawadatul Maulidah; Andrian Eko Widodo; Rachmawati Darma Astuti
CONTEN : Computer and Network Technology Vol. 5 No. 2 (2025): Desember 2025
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/conten.v5i2.10116

Abstract

E-commerce merupakan media yang memfasilitasi transaksi komersial antara individu dengan individu maupun antara individu dan organisasi melalui sistem daring. Salah satu bentuk implementasi e-commerce adalah aplikasi Shopee. Shopee dikembangkan sebagai aplikasi berbasis perangkat mobile yang memungkinkan pengguna melakukan aktivitas belanja secara online dengan mudah, sehingga transaksi dapat dilaksanakan dimanapun dan kapanpun. Aplikasi tersebut tentunya mempunyai kekurangan dan kelebihan yang dirasa oleh masyarakat. Dari adanya kekurangan dan kelebihan aplikasi shopee tidak sedikit masyarakat yang memberikan ulasan negatif maupun positif terhadap aplikasi tersebut. Pemanfaatan data dalam jumlah besar dapat dilakukan melalui penerapan teknik Data Mining. Penelitian ini bertujuan untuk menganalisis berbagai masalah yang dituju terhadap pengguna terhadap aplikasi Shopee di Google Play Store serta mengukur tingkat akurasi analisis sentimen yang dihasilkan menggunakan algoritma K-Nearest Neighbors (KNN). Menghasilkan bahwa dengan algoritma KNN diperoleh nilai akurasi Pred.Negatif nilainya sebesar 69,59%. Hasil dari Pred.Positif nilainya sebesar 71,70%.  Sedangkan nila accuracy 70,51% dan nilai AUC sebesar  0.804 +/- 0.053 (mikro: 0.804) (positive class: Positif).   E-commerce is a means of commercial transactions between individuals and organizations or a buying and selling transaction conducted online. One example of e-commerce implementation is the Shopee application. Shopee is available in the form of a mobile phone application that makes it easier for users to shop online, allowing access anytime and anywhere. Of course, this application has advantages and disadvantages perceived by the public. Due to the application’s strengths and weaknesses, many users provide both positive and negative reviews of the app. Techniques for utilizing large amounts of data can be applied through Data Mining. The purpose of this research is to analyze issues related to several reviews of the Shopee application on Google Play Store and to determine the accuracy results of sentiment analysis generated using the KNN (K-Nearest Neighbors) algorithm. The result showed that with KNN algorithm obtained the value of Pred. Negative accuracy value of 69.59%. Results from Pred. Positive value of 71.70%.  While accuracy value 70.51% and AUC value of 0804 +/-0053 (Micro: 0804) (positive class: positives).