An Explainable AI-Driven Framework for Risk-Adaptive Security and Selective Auditing of Cloud Virtual Machines Paper II: Explainable Threat Detection and Context-Aware Access Risk Assessment

Virendra Singh Thakur; Dipti Sharma

An Explainable AI-Driven Framework for Risk-Adaptive Security and Selective Auditing of Cloud Virtual Machines Paper II: Explainable Threat Detection and Context-Aware Access Risk Assessment

Author(s)	Mr. Virendra Singh Thakur, Ms. Dipti Sharma
Country	India
Abstract	Authenticated cloud requests can remain harmful when credentials are stolen, roles are misused or activity departs from an identity’s normal behaviour. Static access rules verify permission but do not fully describe behavioural intent. This paper presents an explainable machine-learning framework for classifying cloud virtual-machine (VM) access events and combining probabilistic evidence with deterministic security policy. A synthetic dataset of 60,000 events is generated for 400 VMs and 120 identities using credential-misuse, anomalous update, data-exfiltration and reconnaissance scenarios. Logistic regression, support vector machine, random forest and gradient boosting are evaluated under a common 70/15/15 stratified split. Gradient boosting achieves 96.8% accuracy, 96.0% precision, 97.0% recall and a 96.5% F1-score on the held-out simulation data. A policy-first composite response retains 100% coverage of predefined critical cases, while an ML-only configuration covers 94.1%. Component scores and reason codes explain whether a response is driven by VM sensitivity, auditor suitability, behavioural probability or policy. Results are limited to the controlled simulation and should not be interpreted as production detection rates
Keywords	cloud security, anomaly detection, explainable machine learning, virtual machines, gradient boosting, access control
Field	Engineering
Published In	Volume 7, Issue 4, July-August 2026
Published On	2026-08-28

View / Download PDF File

E-ISSN 3048-7641

doi

CrossRef DOI is assigned to each research paper published in our journal.

AIJFR DOI prefix is
10.63363/aijfr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 4 Cover Page Vol 7 Isu 3 Cover Page Vol 7 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 AIJFR 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		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research

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

An Explainable AI-Driven Framework for Risk-Adaptive Security and Selective Auditing of Cloud Virtual Machines Paper II: Explainable Threat Detection and Context-Aware Access Risk Assessment

Share this