Skip to main content

Monika Roopak

Intrusion detection system against DDoS attack in IoT networks.

Email: m.roopak2@ncl.ac.uk

Project title

Intrusion detection system against DDoS attack in IoT networks

Supervisors

Project description

We are building a defense mechanism to secure Internet of Things systems. Our real-time Intrusion Detection System uses deep learning techniques for monitoring network parameters. It will identify distributed denial of service (DDoS) attacks. It will react quickly to hacking attacks and malicious activities in a resource-constrained IoT.

Methodology and objectives

We have divided the work into two stages:

  1. selecting features using a multi-objective optimisation-based algorithm to reduce the dimensionality of the data
  2. building a classifier using deep learning methods for the detection of attack on the network

We will:

  • review challenges and recent cyber-attacks in IoT
  • propose a novel scheme for data selection using an NSGA-III multi-objective optimisation algorithm
  • design an advanced Intrusion Detection System based on deep learning for the detection of DDoS cyber-attack on IoT networks

Result

Our results based on the proposed methods are satisfactory in terms of confusion metrics. We have compiled all the results in research papers and submitted them for publication.

Publications

  • Poster: A review of Intrusion Detection Schemes for IoT networks (ARC 2017)
  • Conference paper: Improved NSGA-III for solving multi-objective optimization problems (ARC 2018)
  • Conference paper: Deep Learning Models for Cyber Security in IoT Networks. In: IEEE CCWC 2019, USA
  • Conference paper: Intrusion Detection System against DDoS Attack in IoT Networks (submitted)
  • Conference paper: Multi-Objective based Feature Selection for DDoS Attack Detection in IoT Network (submitted)

Interests

Deep Learning, Machine Learning, Data Science

Qualifications

  • MTech (Information Technology)