KERANGKA FORENSIK JARINGAN BERBASIS NEURAL NETWORK UNTUK DETEKSI DAN ANALISIS SERANGAN SIBER
Penulis
-
Hafidz Budiman
Universitas Labuhanbatu
-
Ferdy Ardiansyah
Universitas Labuhanbatu
-
Sahat Parulian Sitorus
Universitas Labuhanbatu
-
Eriski Aulia Rahmi
Universitas Labuhanbatu
-
Siti Sarah
Universitas Labuhanbatu
-
Wulan Inda Sari
Universitas Labuhanbatu
https://doi.org/10.47561/jtik.v19i1.350
This Abstract has been read 64 times
Abstrak
Peningkatan kompleksitas serangan siber menuntut metode forensik jaringan yang mampu merekonstruksi, mendeteksi, dan menafsirkan aktivitas berbahaya secara akurat. Pendekatan forensik yang ada masih menghadapi keterbatasan dalam analisis lalu lintas jaringan berskala besar, terutama ketika pola serangan menyerupai aktivitas normal sehingga menyulitkan proses identifikasi insiden dan rekonstruksi kronologi kejadian. Penelitian ini mengusulkan kerangka forensik jaringan berbasis neural network yang mengintegrasikan proses identifikasi serangan, klasifikasi lalu lintas jaringan, serta rekonstruksi aktivitas komunikasi untuk mendukung investigasi digital. Penelitian menggunakan desain eksperimental dengan dataset trafik jaringan yang terdiri atas aktivitas normal dan aktivitas berbahaya, meliputi scanning jaringan, brute force pada layanan autentikasi, serangan denial of service, serta distribusi malware. Model neural network digunakan pada tahap deteksi untuk mengklasifikasikan trafik jaringan, sementara pipeline forensik terstruktur digunakan untuk mengekstraksi artefak digital dan melakukan korelasi metadata jaringan. Hasil penelitian menunjukkan bahwa model yang diusulkan mencapai tingkat akurasi sebesar 97,82 persen dengan nilai false positive rate yang rendah serta waktu pemrosesan yang lebih singkat dibandingkan pendekatan forensik konvensional. Analisis forensik terhadap log jaringan menunjukkan pola serangan yang konsisten dengan karakteristik scanning pada port layanan umum, percobaan autentikasi berulang pada layanan SSH, anomali interval waktu paket pada serangan denial of service, serta peningkatan entropi payload pada komunikasi malware. Temuan ini menunjukkan efektivitas integrasi neural network dalam meningkatkan kemampuan deteksi serta mendukung proses rekonstruksi artefak digital dalam investigasi forensik jaringan.
Keywords: forensik jaringan, investigasi digital, neural network, serangan siber
CITATIONS
Unduhan
Referensi
B. Y. Pratama and others, “Network forensic analysis using NIST 800-86 approach for detecting malicious activities,” J. Ilmu Komput. dan Inf., vol. 16, no. 2, pp. 123–134, 2023.
A. Meshram and C. Haas, “Malware forensics analysis using memory reconstruction and deep learning,” Digit. Investig., vol. 40, p. 301400, 2022.
A. K. B. Arnob and A. Roy, “A comprehensive systematic review of intrusion detection systems using deep learning and feature engineering,” J. Emerg. Cybersecurity, 2025.
D. Spiekermann and others, “Deep learning for network intrusion detection in virtual networks,” Electronics, vol. 13, no. 18, p. 3617, 2024.
I. H. Sarker, “Deep learning-based cybersecurity: A survey of threats, datasets, and methods,” Artif. Intell. Rev., vol. 55, no. 6, pp. 4491–4558, 2022.
N. Moustafa and others, “Federated deep learning-based intrusion detection in IoT networks,” IEEE Trans. Netw. Sci. Eng., vol. 9, no. 3, pp. 1653–1667, 2022.
M. Farhan and others, “Network-based intrusion detection using sequential deep neural networks and feature selection in realistic network traffic,” Sci. Rep., vol. 15, p. 22719, 2025.
H. Kim and J. Park, “Machine learning-based malicious traffic detection using flow statistical features,” Sensors, vol. 22, no. 6, p. 2388, 2022.
Y. Yu and others, “A hybrid CNN-GRU model for encrypted traffic classification in network security,” Inf. Sci. (Ny)., vol. 624, pp. 433–447, 2023.
L. Silva and others, “A deep learning-based incident classification model for SOC-level response,” J. Netw. Comput. Appl., vol. 229, p. 103676, 2024.
R. A. Ramadhan, A. T. Tira, and M. R. Fadhilah, “Network Forensic: Analysis of client attack and QoS measurement by ARP poisoning using NFGP model,” Sistemasi, vol. 13, no. 2, pp. 713–727, 2024.
M. A. Ferrag and L. Maglaras, “Deep learning for cyber security intrusion detection: Approaches and datasets,” Appl. Sci., vol. 11, no. 10, p. 4385, 2021.
S. Bhardwaj and M. Dave, “Enhanced neural network--based attack investigation framework for network forensics: Identification, detection, and analysis of the attack,” Comput. & Secur., vol. 135, p. 103521, 2023.
A. P. AbdelHalim and M. Hassan, “Deep learning techniques for network intrusion detection systems: Recent advances and challenges,” Int. J. Comput. Inf. Sci., 2025.
X. Zhang and others, “Malicious traffic detection based on multi-feature fusion and deep neural networks,” Futur. Gener. Comput. Syst., vol. 143, pp. 312–327, 2023.
S. Rahman and others, “AI-driven digital evidence examination and incident response automation,” IEEE Trans. Inf. Forensics Secur., vol. 19, pp. 2222–2236, 2024.
A. Mansour and others, “Automated cyber-attack investigation using sequence-aware neural models,” Expert Syst. Appl., vol. 228, p. 120352, 2023.
V. Sharma and others, “Digital forensics for cybercrime investigation using machine learning: A comprehensive analysis,” Forensic Sci. Int. Digit. Investig., vol. 48, p. 301551, 2024.
M. Latah, “Deep learning approaches for intrusion detection systems: A survey,” Adv. Eng. Informatics, vol. 48, p. 101299, 2021.
A. Alqahtani and others, “A collaborative deep learning model for DDoS attack detection in cloud environments,” IEEE Access, vol. 11, pp. 45731–45749, 2023.
##submission.downloads##
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Hafidz Budiman, Ferdy Ardiansyah, Sahat Parulian Sitorus, Eriski Aulia Rahmi, Siti Sarah, Wulan Inda Sari
This work is licensed under a Creative Commons Attribution 4.0 International License.
