Machine learning and metaheuristic optimization algorithms for feature selection and botnet attack detection

Knowledge and Information Systems, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 13, 2025

Language: Английский

A Graphical Approach for Botnet Detection in IoT Edge Environments Using a Lightweight Dynamic Louvain Method

Internet Technology Letters, Journal Year: 2025, Volume and Issue: 8(2)

Published: March 1, 2025

ABSTRACT The increasing adoption of Internet Things (IoT) devices has increased the risk botnet attacks, posing significant threats to device integrity, network performance, and user privacy. Existing detection methods rely on computationally intensive flow analysis, which is not suitable for resource‐constrained IoT edge environments. This study introduces a novel graphical approach using lightweight dynamic Louvain method. method dynamically constructs temporal graphs where nodes represent edges capture interactions. graph topological features are extracted, weights integrated based communication patterns. communities identified in by applying method, anomalies community structure analyzed detect activities. Experimental evaluations BoT‐IoT dataset show that proposed achieves 99.3% accuracy, 99.1% precision, recall, F1‐score. Further, compared with traditional graph‐based approaches demonstrates superior performance terms speed, scalability, resource efficiency.

Language: Английский

Ensemble of deep learning models with Walrus Optimization Algorithm for accurate botnet recognition and classification

Iran Journal of Computer Science, Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

Language: Английский