EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Driven SOC Analyst for Automated Cyber Threat Detection and Response

Manthan Khujnare, Kaushik Ninave, Aniruddha Potphode, Trisha Poreddiwar, Arya Kamdi, Bhakti Thakre

Journal of Integrated Engineering Sciences · 25.10.2026 · 2 (4) · 23-39

DOI: 10.63686/jies.v2i4042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Integrated Engineering Sciences, online erschienen am 25.10.2026. Verfasst von Manthan Khujnare und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Security Operations Centers (SOCs) play an important role in identifying, analyzing, and responding to cybersecurity threats. However, the increasing volume of security alerts and network traffic makes manual threat detection and investigation challenging. This research presents an AI-Driven SOC Analyst designed to support automated cyber threat detection, risk assessment, and incident analysis using machine learning techniques. The proposed system combines machine learning-based anomaly detection and threat classification to analyze security data and identify potentially malicious activities. The framework incorporates data preprocessing, feature scaling, anomaly detection using Isolation Forest, and classification using a Random Forest model. Detected events can be assigned risk scores to help prioritize security incidents. The system also aims to associate identified threats with relevant MITRE ATT&CK techniques and provide understandable summaries to assist security analysts in investigating suspicious activities. A web-based dashboard supports the visualization and monitoring of detected events, while a backend API manages data processing and communication between system components. The proposed approach aims to reduce repetitive manual analysis, improve alert prioritization, and support faster incident investigation. The effectiveness of the system should be evaluated using appropriate detection metrics, including precision, recall, F1-score, and false-positive rate. The framework provides a foundation for developing an affordable, AI-assisted security monitoring solution for educational environments and small organizations.

Zitieren

APA

Khujnare, M., Ninave, K., Potphode, A., Poreddiwar, T., Kamdi, A., & Thakre, B. (2026). AI-Driven SOC Analyst for Automated Cyber Threat Detection and Response. Journal of Integrated Engineering Sciences, 2(4), 23-39. https://doi.org/10.63686/jies.v2i4042

Vancouver

Khujnare M, Ninave K, Potphode A, Poreddiwar T, Kamdi A, Thakre B. AI-Driven SOC Analyst for Automated Cyber Threat Detection and Response. Journal of Integrated Engineering Sciences. 2026;2(4):23-39. doi:10.63686/jies.v2i4042

BibTeX
@article{Khujnare2026,
  author = {Khujnare, Manthan and Ninave, Kaushik and Potphode, Aniruddha and Poreddiwar, Trisha and Kamdi, Arya and Thakre, Bhakti},
  title = {AI-Driven SOC Analyst for Automated Cyber Threat Detection and Response},
  journal = {Journal of Integrated Engineering Sciences},
  year = {2026},
  volume = {2},
  number = {4},
  pages = {23--39},
  doi = {10.63686/jies.v2i4042}
}
Kostenlos starten →