Remembering Everything Makes You Vulnerable: A Limelight on Machine Unlearning for Personalized Healthcare Sector

TL;DR

This paper introduces Machine Unlearning to improve privacy and robustness of personalized ECG healthcare models by removing sensitive data points, thereby reducing vulnerability to adversarial attacks without sacrificing model accuracy.

Contribution

It presents a novel Machine Unlearning algorithm tailored for personalized ECG models to enhance privacy and defend against adversarial attacks.

Findings

Machine Unlearning effectively mitigates adversarial attack impact.

Personalized ECG models remain accurate after unlearning.

Enhanced model robustness against FGSM attacks.

Abstract

As the prevalence of data-driven technologies in healthcare continues to rise, concerns regarding data privacy and security become increasingly paramount. This thesis aims to address the vulnerability of personalized healthcare models, particularly in the context of ECG monitoring, to adversarial attacks that compromise patient privacy. We propose an approach termed "Machine Unlearning" to mitigate the impact of exposed data points on machine learning models, thereby enhancing model robustness against adversarial attacks while preserving individual privacy. Specifically, we investigate the efficacy of Machine Unlearning in the context of personalized ECG monitoring, utilizing a dataset of clinical ECG recordings. Our methodology involves training a deep neural classifier on ECG data and fine-tuning the model for individual patients. We demonstrate the susceptibility of fine-tuned models to adversarial attacks, such as the Fast Gradient Sign Method (FGSM), which can exploit additional data points in personalized models. To address this vulnerability, we propose a Machine Unlearning algorithm that selectively removes sensitive data points from fine-tuned models, effectively enhancing model resilience against adversarial manipulation. Experimental results demonstrate the effectiveness of our approach in mitigating the impact of adversarial attacks while maintaining the pre-trained model accuracy.