Home / Current Issue / Paper 1712992
AI-Powered Security Information and Event Management: A Review of Deep Learning Approaches for Modern Cybersecurity
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
Abstract
Cyber threats are increasing with rapidly emerging digital infrastructure. In that scenario, even a reasonable pace cannot be maintained by traditional SIEM systems. Deep learning technologies such as Variational Autoencoders and Graph Neural Networks have to be embedded into SIEMbased systems so that anomaly activity might be detected and zero-day threats also identified with accurate and timely generation of the alerts. We critically compare recent advances in deep learning-based SIEM with their more practical applications in detecting complex cyberattacks and focus on how AI improves the effectiveness of the efficacy of reports from SIEMs and technical challenges associated with those methodologies.
Keywords
Deep Learning, Variational Autoencoder (VAE), Graph Neural Network (GNN), Anomaly Detection, Cybersecurity and Security Information and Event Management (SIEM).
References
[1] Tao Ban, Takeshi Takahashi, Samuel Ndichu and Daisuke Inoue " Breaking Alert Fatigue: AI-Assisted SIEM Framework for Effective Incident Response." Appl. Sci. 2023, 13, 6610. https://doi.org/10.3390/app13116610
[2] Srinivas Reddy Pulyala , " The Future of SIEM in a Machine Learning - Driven Cybersecurity Landscape.
[3] Srinivas Reddy Pulyala , " From Detection to Prediction : AI Powered SIEM for Proactive Threat Hunting and Risk Mitigation.
[4] Srinivas Reddy Pulyala, Vinay Dutt Jangampet, Avinash Gupta Desetty " REVOLUTIONIZING SIEM WITH ML-DRIVEN RISK ASSESSMENT AND PRIORITIZATION"
[5] Gattani Tanuj Subhash, Dr. S Anupama Kumar, " Artificial Intelligence Approaches to Uncover Cyber Security"
[6] Chen, Y., Wang, Z., Li, J., "A Survey of Artificial Intelligence in Cybersecurity," IEEE Access, Vol. 11, pp. 3153-3170, 2023.
[7] Zhang, Y., Liu, J., Chen, H., "Artificial Intelligence for Cybersecurity: A Review of Approaches, Challenges, and Open Research Problems," Frontiers in Cybersecurity, Vol. 3, Article 668686, 2022.
[8] Hsiao, K., Yang, C., "Using Machine Learning for Intrusion Detection: A Review," Journal of Information Security and Applications, Vol. 70, Article 102428, 2022.
[9] "Artificial Intelligence in Cybersecurity: Challenges, Advances, and Future Perspectives" by C. Liang, R. Zhang, and Y. Liu - Computers & Security, Vol. 118, pp. 102426, 2022.
[10] "Machine Learning for Cyber Threat Intelligence: A Survey" by M. Ahmadi, M. Dehghantanha, K. Choo, and S. Singh - Journal of Network and Computer Applications, Vol. 188, pp. 103049, 2021.
How to cite this paper
@article{1712992,
author = {Sufia Begum D, Chinmaye D M, Poorna shree P, Nandana C K, Nithish Kumar K S},
title = {AI-Powered Security Information and Event Management: A Review of Deep Learning Approaches for Modern Cybersecurity},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {6},
pages = {1313-1318},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1712992.pdf},
abstract = {Cyber threats are increasing with rapidly emerging digital infrastructure. In that scenario, even a reasonable pace cannot be maintained by traditional SIEM systems. Deep learning technologies such as Variational Autoencoders and Graph Neural Networks have to be embedded into SIEMbased systems so that anomaly activity might be detected and zero-day threats also identified with accurate and timely generation of the alerts. We critically compare recent advances in deep learning-based SIEM with their more practical applications in detecting complex cyberattacks and focus on how AI improves the effectiveness of the efficacy of reports from SIEMs and technical challenges associated with those methodologies.},
keywords = {Deep Learning, Variational Autoencoder (VAE), Graph Neural Network (GNN), Anomaly Detection, Cybersecurity and Security Information and Event Management (SIEM).},
month = {December},
doi = {https://doi.org/10.64388/IREV9I6-1712992}
}