A Heterogenous IoT Attack Detection Through Deep Reinforcement Learning: A Dynamic ML Approach

Roshan Baby; Zahra Pooranian; Mohammad Shojafar; Rahim Tafazolli

doi:10.1109/ICC45041.2023.10278685

Back

Conference proceeding

A Heterogenous IoT Attack Detection Through Deep Reinforcement Learning: A Dynamic ML Approach

Roshan Baby, Zahra Pooranian, Mohammad Shojafar and Rahim Tafazolli

ICC 2023 - IEEE International Conference on Communications, pp.479-484

28/05/2023

DOI: https://doi.org/10.1109/ICC45041.2023.10278685

Abstract

Adaptation models

Artificial intelligence

Deep learning

Deep Reinforcement Learning

Defence

Intrusion detection

Intrusion Detection System

Label Flipping Attack

Reinforcement learning

Internet of Things

Machine Learning

This paper presents an innovative Intrusion Detection System (IDS) architecture using Deep Reinforcement Learning (DRL). To accomplish this, we started by analysing the DRL issue for IoT devices, followed by designing intruder attacks using Label Flipping Attack (LFA). We propose an artificial intelligence DRL model to imitate IoT attack detection, along with two defence strategies: Label-based Semi-supervised Defence (LSD) and Clustering-based Semi-supervised Defence (CSD). Finally, we provide the evaluation results of the adaptive attack and defence models on multiple IoT scenarios with the NSL-KDD, IoT-23, and NBaIoT datasets. The research proves that DRL functions effectively with dynamically produced traffic in contrast to existing conventional techniques.

Metrics

27 Record Views

Details

Title: A Heterogenous IoT Attack Detection Through Deep Reinforcement Learning: A Dynamic ML Approach
Creators: Roshan Baby (Author) - University of Surrey, School of Computer Science and Electronic Engineering
Zahra Pooranian - University of Surrey, School of Computer Science and Electronic Engineering
Mohammad Shojafar - University of Surrey, School of Computer Science and Electronic Engineering
Rahim Tafazolli - University of Surrey, School of Computer Science and Electronic Engineering
Publication Details: ICC 2023 - IEEE International Conference on Communications, pp.479-484
Publisher: IEEE
Date published: 28/05/2023
Identifiers: 99826164802346
Copyright: Request permission for reuse.
Academic Unit: School of Computer Science and Electronic Engineering; Institute for Sustainability
Language: English
Resource Type: Conference proceeding

A Heterogenous IoT Attack Detection Through Deep Reinforcement Learning: A Dynamic ML Approach

Abstract

Metrics

Details

Usage Policy