Analisis Kinerja Deep Learning Berbasis Convolutional Neural Network (CNN) untuk deteksi Dini SQl Injection
DOI:
https://doi.org/10.62712/juktisi.v5i1.964Keywords:
Deep Learning, 1D-CNN, Keamanan Siber, Datacenter Diskominfo BinjaiAbstract
Serangan SQL Injection (SQLi) merupakan ancaman kritis bagi keamanan layanan publik berbasis web di lingkungan pemerintahan. Metode deteksi tradisional sering kali mengalami keterbatasan dalam menangani payload yang disamarkan (obfuscated) dan memerlukan rekayasa fitur manual yang kompleks. Penelitian ini bertujuan untuk menganalisis kinerja arsitektur Deep Learning berbasis 1D-Convolutional Neural Network (1D-CNN) untuk deteksi dini serangan SQLi, dengan studi kasus pada Datacenter Diskominfo Kota Binjai. Metodologi penelitian mencakup pemrosesan dataset sebanyak 19.078 baris log akses server web riil yang dibagi menggunakan metode Hold-out Validation dengan proporsi 80% data latih dan 20% data uji. Arsitektur 1D-CNN dirancang untuk melakukan pemrosesan teks sekuensial guna mengekstrak fitur leksikal lokal secara otomatis langsung dari log mentah. Hasil evaluasi menunjukkan performa klasifikasi yang sangat superior dengan tingkat Akurasi 100%, Presisi 99%, dan Recall 97% pada identifikasi serangan. Penelitian ini menyimpulkan bahwa model 1D-CNN sangat handal dan efisien untuk diimplementasikan sebagai sistem peringatan dini (early warning system) tanpa mengganggu kinerja operasional layanan publik di lingkungan Pemerintah Kota Binjai.
Downloads
References
R. Israyudin, F. M. Arrofi, and A. R. Dwiardi, “Digital Transformation through Electronic-Based Government System Policy in Indonesia: A Policy Narrative Analysis,” J. La Soc., vol. 6, no. 2, pp. 281–292, 2025, doi: 10.37899/journal-la-sociale.v6i2.1825.
H. P. Fitrian, M. N. Khaerudin, M. R. Umarulloh, R. Ahmad, and A. R. Agustin, “Systematic Literature Review : Peran Artificial Intelligence dalam Meningkatkan Akurasi Deteksi SQL Injection pada Aplikasi Web,” no. 1, pp. 1–10, 2026.
S. S. Ahmed and M. L. Al Dabag, “Machine Learning and Deep Learning Approaches for Accent Recognition: A Review,” IEEE Access, vol. 13, pp. 51527–51550, 2025, doi: 10.1109/ACCESS.2025.3552935.
S.R. Menaka, “An Efficient SQL Injection Detection with a Hybrid CNN & Random Forest Approach,” J. Inf. Syst. Eng. Manag., vol. 10, no. 18s, pp. 664–673, 2025, doi: 10.52783/jisem.v10i18s.2979.
M. Shahbaz, G. Mumtaz, S. Zubair, and M. Rehman, “Evaluating CNN Effectiveness in SQL Injection Attack Detection,” J. Comput. & …, vol. 07, no. 02, 2024.
H. Sun, Y. Du, and Q. Li, “Deep Learning-Based Detection Technology for SQL Injection Research and Implementation,” Appl. Sci., vol. 13, no. 16, 2023, doi: 10.3390/app13169466.
Y. Chen, G. Liang, and Q. Wang, “Research on SQL Injection Detection Technology Based on Content Matching and Deep Learning,” Comput. Mater. Contin., vol. 84, no. 1, pp. 1145–1167, 2025, doi: 10.32604/cmc.2025.063319.
F. D. Hafriadi and R. Ardiansyah, “NETWORK’S ACCESS LOG CLASSIFICATION FOR DETECTING SQL INJECTION ATTACKS WITH THE LSTM ALGORITHM,” J. Tek. Inform., vol. 5, no. 4 SE-Articles, pp. 745–752, Sep. 2024, doi: 10.52436/1.jutif.2024.5.4.2157.
F. Alghamdi and B. Ben Ammar, “Enhancing SQL Code Security and Maintainability: A Deep Learning Based Approach,” Int. J. Adv. Artif. Intell. Mach. Learn., vol. 2, no. 3, pp. 160–169, 2025, doi: 10.58723/ijaaiml.v2i3.515.
H. Yu et al., “Multi-Agent Honeypot-Based Request-Response Context Dataset for Improved SQL Injection Detection Performance,” pp. 2–6, 2026.
R. T. Lo, W. J. Hwang, and T. M. Tai, “SQL Injection Detection Based on Lightweight Multi-Head Self-Attention,” Appl. Sci., vol. 15, no. 2, pp. 1–17, 2025, doi: 10.3390/app15020571.
B. Turarov and S. Kabdrakhova, “OPTIMIZING CONVOLUTIONAL NEURAL NETWORKS FOR REAL-TIME SQL INJECTION DETECTION IN POSTGRESQL DATABASES WITH A FOCUS ON REDUCING FALSE POSITIVES,” vol. 6, no. 135, 2025.
N. Rachana, N. Kshama, S. S. Venki, R. Prajwal, and N. Thanuja, “Injectiq : ML-Powered SQL Injection Detection For Saas Applications,” vol. 13, no. 12, 2025.
D. S. W. Nguyen, D. F. Alrubie, D. S. W. Nguyen, and D. F. Alrubie, “Designing a Detection Model for SQL Injection Attack,” J. Comput. Commun., vol. 13, no. 08, pp. 40–79, Aug. 2025, doi: 10.4236/jcc.2025.138003.
B. M. Hassn, E. S. Alomari, J. S. Alrubaye, and O. A. Hassen, “Adversarially Robust 1D-CNN for Malicious Traffic Detection in Network Security Applications,” J. Cybersecurity Inf. Manag., vol. 16, no. 1, pp. 162–175, 2025, doi: 10.54216/JCIM.160113.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Khairul, Muhammad Azuan, Toni Prabowo, Aradi Sebayang, Tengku Didi Ferdillah
This work is licensed under a Creative Commons Attribution 4.0 International License.
