The Use of Artificial Intelligence for Cyber Threat Detection: A Systematic Literature Review of Research Methods, Accuracy, and Gaps
Keywords:
Artificial Intelligence, Cyber Threat Detection, Machine Learning, Deep Learning, Cybersecurity, PRISMA, Systematic Literature ReviewAbstract
This study presents a comprehensive Systematic Literature Review (SLR) on the use of Artificial Intelligence (AI) for cyber threat detection, focusing on methods, accuracy levels, and research gaps from the last five years. A total of 47 eligible studies were analyzed using the PRISMA framework. The findings show that deep learning has become the dominant approach, outperforming traditional machine learning in identifying complex threats such as DDoS, zero-day attacks, and advanced malware. Hybrid models also demonstrate high accuracy, exceeding 95% in several datasets. However, significant gaps remain, including limited real-time evaluations, outdated public datasets, insufficient research on explainable AI, and the lack of adversarial defense mechanisms. This review emphasizes the need for more robust, interpretable, and adaptive AI-based security systems to address evolving cyber threats effectively. The results provide essential insights and guidance for future research in AI-driven cybersecurity.
References
M. Ahmed, A. Mahmood, and J. Hu, "A survey of network anomaly detection techniques," Journal of Network and Computer Applications, vol. 168, pp. 102–124, 2020.
S. Garg, A. Singh, and P. Kaur, "Machine learning for cybersecurity: A comprehensive survey," Computers & Security, vol. 112, pp. 102498, 2021.
A. Javaid, Q. Niyaz, W. Sun, and M. Alam, "A deep learning approach for network intrusion detection," IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 5, no. 4, pp. 563–575, 2021.
K. Kim and J. Park, "Cyber threat detection using deep learning-based behavioral analysis," IEEE Access, vol. 9, pp. 14592–14604, 2021.
R. Shapira and A. Shabtai, "Adversarial machine learning in intrusion detection: A systematic review," ACM Computing Surveys, vol. 54, no. 10, pp. 1–36, 2022.
H. Hussain, S. Abubakar, and R. Malik, "Explainable AI for cybersecurity threat classification," IEEE Access, vol. 10, pp. 88524–88539, 2022.
Y. Zhang, X. Chen, and L. Wang, "A transformer-based approach for detecting advanced persistent threats (APT)," Future Generation Computer Systems, vol. 142, pp. 350–362, 2023.
M. T. Khan and A. Anwar, "Hybrid AI models for next-generation intrusion detection systems," Information Sciences, vol. 622, pp. 112–131, 2023.
S. Li, Y. Fang, and H. Yan, "Systematic review of AI-driven malware detection methods," IEEE Transactions on Information Forensics and Security, vol. 18, pp. 2301–2316, 2023.
F. Hu, Y. Zhu, and L. Xia, "Towards resilient intrusion detection: Evaluating robustness under adversarial attacks," Computers & Security, vol. 127, pp. 103102, 2023.
M. Georgescu, A. Ionescu, and C. Dobre, "A systematic literature review of artificial intelligence for cyber threat detection," Sensors, vol. 23, no. 4, pp. 2150, 2023.
J. Lin and W. Li, "Data imbalance and feature drift in intrusion detection datasets: A review of challenges and solutions," Expert Systems With Applications, vol. 232, pp. 120844, 2024.
L. Ahmed and B. Li, "Evaluating AI-based threat detection on real-world network traffic: A gap between theory and practice," IEEE Transactions on Network and Service Management, vol. 21, no. 2, pp. 21. 155–170, 2024.
S. Moradi and P. Zargar, "Enhancing intrusion detection accuracy through multi-modal deep learning fusion," Applied Soft Computing, vol. 151, pp. 110046, 2024.
T. Nakamura, R. Sato, and K. Yamada, "Benchmarking AI-powered cybersecurity systems: A PRISMA-guided review," Journal of Information Security and Applications, vol. 78, pp. 103603, 2024.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Journal of Computing and Smart Ecosystems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
