Real-Time Detection and Prevention of IOT-Based DDOS Attacks in Network Environments
Toala Dimabo Briggs
Source record
Source: Crossref
Published: Oct 8, 2026
DOI: 10.56201/ijasmt.vol.12.no9.2026pg24.33
Open original source ↗Source abstract
The rapid growth of Inter-of-Things (IoT) devices and their weak security configurations have significantly increased the vulnerability of modern network infrastructures to different forms of sophisticated cyber-attacks, particularly low-rate, stealthy, and botnet-driven DDoS attacks. Existing traditional intrusion detection and prevention systems often suffer from high latency, poor adaptability to evolving attack patterns, inadequate real-time response mechanisms, and limited privacy-preserving capabilities. Therefore, to address these limitations, this paper presents a real time intelligent framework for the analysis, detection, and prevention of IoT-based Distributed Denial of Service (DDoS) attacks in network environments. The developed system utilized Long Short-Term Memory (LSTM) as the core real-time detection engine for identifying malicious IoT traffic patterns based on temporal and behavioral network features, and Reinforcement Learning (RL) technique to design an intelligent automated prevention and response mechanism capable of mitigating malicious traffic patterns dynamically. Furthermore, Homomorphic Encryption (HE) using the Cheon-Kim-Kim-Song (CKKS) scheme was integrated into the framework to preserve the privacy of sensitive network traffic during storage, analysis and transmission. The system was implemented using Python programming language, while MongoDB served as the NoSQL database for data storage and management. Experimental results showed that the proposed system achieved an excellent detection and prevention performance, recording a detection accuracy of 98.3%, precision of 97.8%, recall of 98.6%, and F1-score of 98.2%. Similarly, the reinforcement learning prevention module achieved an attack-blocking accuracy of 99.2% with a low false positive rate of 0.8%, confirming its effectiveness in dynamically mitigating malicious traffic while allowing legitimate network communications to proceed uninterrupted.
Evidence graph
No public relationships recorded yet.
Integrity note: This page is a factual metadata record created by deterministic ingestion. It is not a claim that the work moves a mathematical frontier or has been independently verified.