Peningkatan Digital Immune System (DIS) untuk Mendeteksi dan Mitigating Serangan Siber Berbasis AI dengan Forensik Digital Terintegrasi
Abstract
Pesatnya perkembangan Artificial Intelligence (AI) telah memicu munculnya serangan siber yang adaptif dan otonom, sehingga mekanisme keamanan tradisional berbasis signature menjadi tidak efektif. Penelitian ini mengusulkan arsitektur Enhanced Digital Immune System (DIS) sebagai sistem keamanan adaptif closed-loop yang mengintegrasikan lapisan sensing, deteksi anomali berbasis AI, respons otomatis, serta lapisan forensik digital. Berbeda dengan sistem konvensional, integrasi ini memungkinkan pembentukan AI Attack Behavioral Signatures untuk analisis pasca-insiden. Evaluasi eksperimental menggunakan serangan adaptive SSH brute-force menunjukkan peningkatan signifikan: tingkat deteksi naik dari 72% menjadi 93%, false positive rate menurun dari 18% menjadi 7%, dan tingkat keberhasilan serangan turun dari 35% menjadi 9%. Selain itu, sistem mencapai waktu respons yang lebih cepat dan meningkatkan kelengkapan bukti forensik dari 40% ke 88%. Temuan ini menunjukkan bahwa DIS secara efektif meningkatkan resiliensi melalui kombinasi respons otomatis dan forensik berbasis kecerdasan. Penelitian ini mempertegas potensi integrasi konsep sistem imun digital dengan forensik untuk menghadapi tantangan keamanan di era AI
Downloads
References
Buczak, A. L., & Guven, E. (2021). Survey of machine learning methods for cyber security intrusion detection. IEEE Communications Surveys & Tutorials, 23(2), 1025–1055.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., et al. (2021). Advances in large language models and autonomous learning systems. Neural Information Processing Systems, 34, 1877–1901.
Carlini, N., Tramèr, F., Wallace, E., Jagielski, M., Herbert-Voss, A., Lee, K., et al. (2023). Extracting training data from large language models. USENIX Security Symposium, 2633–2650.
Conti, M., Dehghantanha, A., Franke, K., & Watson, S. (2022). Security and privacy issues of artificial intelligence systems: A survey. IEEE Communications Surveys & Tutorials, 24(4), 2211–2240.
European Union Agency for Cybersecurity. (2023). ENISA threat landscape 2023. https://www.enisa.europa.eu
European Union Agency for Cybersecurity. (2024). Threat landscape report 2024. https://www.enisa.europa.eu
Gartner. (2023). Top strategic technology trends: Digital immune system. Gartner Research.
Guan, Y., Zhang, Y., & Li, X. (2024). Adaptive cyber defense using AI-driven anomaly detection. Future Generation Computer Systems, 151, 88–102.
Kim, J., Kim, H., & Kim, H. K. (2023). Deep learning-based intrusion detection systems: A comprehensive review. IEEE Access, 11, 12345–12360.
Li, Z., Wang, T., & Sun, Y. (2024). Autonomous cyber defense through adaptive reinforcement learning. Computers & Security, 137, 103512.
Liu, Y., Chen, S., & Xu, H. (2023). Explainable AI for anomaly detection in cybersecurity systems. Expert Systems with Applications, 223, 119902.
National Institute of Standards and Technology. (2024). Cybersecurity framework (CSF) 2.0. https://www.nist.gov
Papernot, N., McDaniel, P., & Goodfellow, I. (2021). Adversarial machine learning in cybersecurity. IEEE Security & Privacy, 19(5), 72–79.
Shafahi, A., Huang, W. R., Najibi, M., et al. (2021). Adversarial attacks and defenses in machine learning-powered systems. IEEE Security & Privacy, 19(3), 65–73.
Singh, A., Sharma, P., & Kumar, R. (2024). AI-powered threat detection systems for next-generation cyber defense. Future Generation Computer Systems, 150, 345–356.
Wang, L., Zhou, J., & Chen, X. (2025). Digital immune systems for adaptive cyber resilience: A next-generation framework. Journal of Information Security and Applications, 82, 103820.
Xin, Y., Kong, L., Liu, Z., et al. (2021). Machine learning and deep learning methods for cybersecurity: A comprehensive review. IEEE Access, 9, 35365–35381.
Zhang, Q., Liu, H., & Zhao, Y. (2025). Behavioral attack signature modeling for AI-driven cyber attacks. IEEE Transactions on Information Forensics and Security, 20, 1440–1455.
Rahman, M., Abdullah, S., & Kim, D. (2026). Intelligent forensic-aware cyber defense architecture for autonomous threat mitigation. Computers & Security, 145, 104001
JISTI
