Spike learning based privacy preservation of Internet of Medical Things in Metaverse

KHOWAJA,, Sunder Ali, DAHRI, Kamran, JARWAR, Muhammad Aslam and LEE, Ik Hyun (2023). Spike learning based privacy preservation of Internet of Medical Things in Metaverse. Journal of Biomedical and Health Informatics (JBHI).

JBHI_paper_rev2 (2).pdf - Accepted Version
Creative Commons Attribution.

Download (25MB) | Preview
Official URL: https://ieeexplore.ieee.org/document/10225265
Link to published version:: https://doi.org/10.1109/JBHI.2023.3306704


With the rising trend of digital technologies, such as augmented and virtual reality, Metaverse has gained a notable popularity. The applications that will eventually benefit from Metaverse is the telemedicine and e-health fields. However, the data and techniques used for realizing the medical side of Metaverse is vulnerable to data and class leakage attacks. Most of the existing studies focus on either of the problems through encryption techniques or addition of noise. In addition, the use of encryption techniques affects the overall performance of the medical services, which hinders its realization. In this regard, we propose Generative adversarial networks and spike learning based convolutional neural network (GASCNN) for medical images that is resilient to both the data and class leakage attacks. We first propose the GANs for generating synthetic medical images from residual networks feature maps. We then perform a transformation paradigm to convert ResNet to spike neural networks (SNN) and use spike learning technique to encrypt model weights by representing the spatial domain data into temporal axis, thus making it difficult to be reconstructed. We conduct extensive experiments on publicly available MRI dataset and show that the proposed work is resilient to various data and class leakage attacks in comparison to existing state-of-the-art works (1.75x increase in FID score) with the exception of slightly decreased performance (less than 3%) from its ResNet counterpart. while achieving 52x energy efficiency gain with respect to standard ResNet architecture.

Item Type: Article
Identification Number: https://doi.org/10.1109/JBHI.2023.3306704
SWORD Depositor: Symplectic Elements
Depositing User: Symplectic Elements
Date Deposited: 14 Aug 2023 16:08
Last Modified: 11 Oct 2023 12:16
URI: https://shura.shu.ac.uk/id/eprint/32265

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics