Deep Learning Approaches for Network Traffic Classification in the Internet of Things (IoT): A Survey

TL;DR

This survey reviews deep learning methods for classifying IoT network traffic, highlighting their strengths, limitations, and future research directions to improve network management and security.

Contribution

It systematically analyzes recent deep learning approaches for IoT traffic classification, identifying research gaps and proposing future directions.

Findings

Deep learning models effectively classify complex IoT traffic patterns.

Current methods face challenges with data variability and resource constraints.

Future research should focus on model efficiency and robustness.

Abstract

The Internet of Things (IoT) has witnessed unprecedented growth, resulting in a massive influx of diverse network traffic from interconnected devices. Effectively classifying this network traffic is crucial for optimizing resource allocation, enhancing security measures, and ensuring efficient network management in IoT systems. Deep learning has emerged as a powerful technique for network traffic classification due to its ability to automatically learn complex patterns and representations from raw data. This survey paper aims to provide a comprehensive overview of the existing deep learning approaches employed in network traffic classification specifically tailored for IoT environments. By systematically analyzing and categorizing the latest research contributions in this domain, we explore the strengths and limitations of various deep learning models in handling the unique challenges posed by IoT network traffic. Through this survey, we aim to offer researchers and practitioners valuable insights, identify research gaps, and provide directions for future research to further enhance the effectiveness and efficiency of deep learning-based network traffic classification in IoT.