Advancing cybersecurity in healthcare using a hybrid deep learning approach for device attack detection
No Thumbnail Available
Authors
Meeting name
Sponsors
Date
Journal Title
Format
Thesis
Subject
Abstract
Cybersecurity has become an important issue in the healthcare industry due to concerns regarding the security of patient information, data from medical devices, and the integrity of healthcare systems. As healthcare becomes more digital, the importance of robust cybersecurity measures is rising. Conventional cybersecurity safeguards often fail to detect and avert sophisticated cyberattacks on healthcare systems. This study proposes a cutting- edge hybrid deep learning strategy to improve hospital cybersecurity to tackle these difficulties. The proposed approach employs deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Partial Least Squares (PLS), feature reduction features and classify unforeseen attacks on healthcare devices. By incorporating these algorithms into the model, we want to provide a comprehensive and flexible approach to threat detection that can detect both established and emerging cybersecurity threat types. Building and testing a hybrid deep learning model tailored to the healthcare industry is the primary focus of this research endeavor. The model proposes extensive testing and validation to ensure it can correctly identify and classify all types of cybercrime, including insider threats, ransomware attacks, malware infections, and more. The model will also be designed to adapt to evolving threat environments, ensuring continuous defense against emerging cybersecurity threats.
Table of Contents
DOI
PubMed ID
Degree
M.S.