A Comprehensive Approach to Cyberattack Detection in Edge Computing Environments

Abstract

This research is concerned with the critical domain of cybersecurity in edge computing environments, which aims to strengthen defenses against increasing cyber threats that target interconnected Internet of Things (IoT) devices. The widespread adoption of edge computing introduces vulnerabilities that necessitate a strong framework for detecting cyberattacks. This study utilizes Long Short-Term Memory (LSTM) networks to present a comprehensive approach based on stacked LSTM layers for detecting and mitigating cyber threats in the dynamic landscape of edge networks. Using the NSL-KDD dataset and rigorous experimentation, this model demonstrates its ability to detect subtle anomalies in network traffic, which can be used to accurately classify malicious activities while minimizing false alarms. The findings highlight the potential of LSTM-based approaches to enhance security at the edge, providing promising avenues for strengthening IoT ecosystems’ integrity and resilience against emerging cyber threats.