Sentinel Sphere: AI-Driven DoS Detection and Mitigation in Cloud

Aathila Fathima M; Aamila Fathima M; Haseena M K

doi:10.36948/ijfmr.2026.v08i04.82461

Sentinel Sphere: AI-Driven DoS Detection and Mitigation in Cloud

Author(s)	Ms. Aathila Fathima M, Ms. Aamila Fathima M, Prof. Haseena M K
Country	India
Abstract	Cloud computing has become an essential platform for hosting modern applications and services, making cloud infrastructures increasingly vulnerable to Denial-of-Service (DoS) attacks that disrupt service availability by overwhelming server resources. Conventional intrusion detection systems primarily rely on rule-based techniques or machine learning models trained on static datasets, limiting their ability to detect evolving attack patterns and respond in real time. This paper presents Sentinel Sphere, an AI-driven framework for real-time DoS detection and automated mitigation in cloud environments. The proposed system continuously monitors NGINX access logs, extracts key traffic features such as Requests Per Second (RPS), IP concentration, endpoint access frequency, and HTTP error rates, and analyzes them using the Mistral 7B Large Language Model deployed locally through the Ollama runtime. Based on contextual reasoning, the framework identifies abnormal traffic behavior and automatically applies mitigation strategies, including request rate limiting and connection control within the NGINX server. The framework was evaluated using ApacheBench-generated attack traffic and benchmark datasets, including CICIDS2017 and NSL-KDD. Experimental results achieved 98.2% detection accuracy, 97.4% precision, 96.8% recall, and a 97.1% F1-score, with an average mitigation response latency of less than 1.2 seconds. The findings demonstrate that integrating Large Language Models with real-time infrastructure monitoring enables adaptive, autonomous, and scalable cybersecurity protection for cloud-hosted web services against evolving DoS attacks.
Keywords	Cloud Computing, Cybersecurity, Denial-of-Service (DoS), Intrusion Detection System, Large Language Models (LLMs), NGINX, Ollama, Mistral 7B, Real-Time Monitoring, Automated Mitigation.
Field	Engineering
Published In	Volume 8, Issue 4, July-August 2026
Published On	2026-07-12
DOI	https://doi.org/10.36948/ijfmr.2026.v08i04.82461

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI prefix of IJFMR is 10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 4 Cover Page Vol 8 Isu 3 Cover Page Vol 8 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Sentinel Sphere: AI-Driven DoS Detection and Mitigation in Cloud

Share this