Event Details
Data Augmentation for IoT Security Attack Detection on Telehealth Model
Presenter: Zaid Ali Khan
Supervisor:
Date: Fri, February 11, 2022
Time: 09:00:00 - 10:00:00
Place: ZOOM - Please see below.
ABSTRACT
Zoom Meeting Link: https://uvic.zoom.us/j/9605499780?pwd=MUdTZzFCUGIrbXB3R3FJbDBTNE5Odz09
Meeting ID: 960 549 9780
Password: 846160
Note: Please log in to Zoom via SSO and your UVic Netlink ID.
Abstract:
Telehealth is an online health care system that is extensively in research these days. The system is comprised of many Internet of Things (IoT) sensors and a central node or server. IoT devices are vulnerable towards threats due to its lack of security. This resulted a dramatic increase in IoT-related attacks and most common attacks are botnet attacks. These botnets are typically used to launch Denial-of-Service (DoS) attacks. In this paper, we introduce a framework that employs various machine learning and data analysis techniques to detect those attacks on IoT devices. We evaluated the effectiveness of the proposed framework using two publicly available datasets from real-world scenarios. These datasets contain a variety of attacks with varying characteristics. Furthermore, the robustness of the proposed framework is tested by combining the two datasets for cross-evaluation. This combination is based on a novel technique for generating supplementary data instances, which employs the GAN (generative adversarial networks) approach to ensure that the number of samples and features are compatible.