AI-Enabled Security Patch Orchestration in Cloud Infrastructure: A Comprehensive Review and Framework for Mitigating Co-Resident DDoS Attacks

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autori principali: Dr.Rethishkumar S, Dr.Anjana S. Chandran
Natura: Recurso digital
Pubblicazione: Zenodo 2026
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901100050776064
author Dr.Rethishkumar S
Dr.Anjana S. Chandran
author_facet Dr.Rethishkumar S
Dr.Anjana S. Chandran
contents <p>This paper presents a comprehensive AI-enabled dynamic security patch orchestration framework designed to mitigate co-resident Distributed Denial of Service (DDoS) attacks in cloud infrastructures. Co-resident attacks exploit shared physical resources such as CPU cache, memory bandwidth, and network I/O between virtual machines (VMs). The proposed framework integrates hybrid Random Forest–Long Short-Term Memory (RF-LSTM) anomaly detection, real-time behavioral monitoring, automated micro-patch deployment, and adaptive feedback learning mechanisms. Extensive simulation using CloudSim with 100–500 VM scenarios demonstrates superior detection accuracy (97.8%), improved precision and recall, and significant reduction in mitigation latency (62% improvement) compared to static patching and signature-based IDS approaches. The framework provides scalable, proactive, and intelligent cloud defense suitable for modern multi-tenant environments.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18697742
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle AI-Enabled Security Patch Orchestration in Cloud Infrastructure: A Comprehensive Review and Framework for Mitigating Co-Resident DDoS Attacks
Dr.Rethishkumar S
Dr.Anjana S. Chandran
<p>This paper presents a comprehensive AI-enabled dynamic security patch orchestration framework designed to mitigate co-resident Distributed Denial of Service (DDoS) attacks in cloud infrastructures. Co-resident attacks exploit shared physical resources such as CPU cache, memory bandwidth, and network I/O between virtual machines (VMs). The proposed framework integrates hybrid Random Forest–Long Short-Term Memory (RF-LSTM) anomaly detection, real-time behavioral monitoring, automated micro-patch deployment, and adaptive feedback learning mechanisms. Extensive simulation using CloudSim with 100–500 VM scenarios demonstrates superior detection accuracy (97.8%), improved precision and recall, and significant reduction in mitigation latency (62% improvement) compared to static patching and signature-based IDS approaches. The framework provides scalable, proactive, and intelligent cloud defense suitable for modern multi-tenant environments.</p>
title AI-Enabled Security Patch Orchestration in Cloud Infrastructure: A Comprehensive Review and Framework for Mitigating Co-Resident DDoS Attacks
url https://doi.org/10.5281/zenodo.18697742