记住一切使你脆弱：聚焦个性化医疗领域的机器遗忘
Remembering Everything Makes You Vulnerable: A Limelight on Machine Unlearning for Personalized Healthcare Sector
AI总结：
本文针对个性化医疗模型在对抗攻击下的隐私脆弱性，提出机器遗忘算法选择性移除敏感数据点，以增强模型鲁棒性并保持预训练模型准确性。
摘要：
随着数据驱动技术在医疗健康领域的普及程度持续上升，对数据隐私与安全的担忧变得日益突出。本论文旨在解决个性化医疗模型在面对危及患者隐私的对抗性攻击时的脆弱性问题，尤其是在心电图（ECG）监测场景下。我们提出一种称为“机器遗忘”（Machine Unlearning）的方法，以减轻已暴露数据点对机器学习模型的影响，从而在保护个人隐私的同时增强模型对对抗性攻击的鲁棒性。具体而言，我们利用临床心电图记录数据集，研究机器遗忘在个性化心电图监测中的有效性。我们的方法包括在心电图数据上训练深度神经分类器，并针对个体患者对模型进行微调。我们证明了微调后的模型容易受到对抗性攻击的影响，例如快速梯度符号法（FGSM），该攻击可以利用个性化模型中额外的数据点。为了解决这一脆弱性，我们提出了一种机器遗忘算法，该算法选择性地从微调模型中移除敏感数据点，从而有效增强模型对对抗性操纵的抵抗能力。实验结果表明，我们的方法在减轻对抗性攻击影响的同时，能够保持预训练模型的准确性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
