arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.14541cs.LGcs.CV
收藏

为什么患者的数据不能轻易被遗忘?

Why patient data cannot be easily forgotten?

University of Edinburgh(爱丁堡大学);The Alan Turing Institute(艾伦·图灵研究所)

Ruolin Su, Xiao Liu, Sotirios A. Tsaftaris

摘要:

数据保护法规中规定的权利允许患者要求数据持有者删除有关其信息的信息。随着人工智能在数据上学习的出现,人们可以想象,这种权利可以扩展到要求在人工智能模型中忘记患者数据的知识。然而,从AI模型中忘记患者的成像数据仍然是一个未被探索的问题。在本文中,我们研究了患者数据对模型性能的影响,并为患者的数据制定了两个假设:要么他们是常见的,与其他患者相似,要么形成边缘情况,即独特和罕见的情况。我们表明,不可能轻易忘记患者数据。我们提出了一种有针对性的遗忘方法来执行病人明智的遗忘。在基准自动心脏诊断挑战数据集上进行的广泛实验显示,与最先进的方法相比,所提出的目标遗忘方法的性能有所改善。

英文摘要:

Rights provisioned within data protection regulations, permit patients to request that knowledge about their information be eliminated by data holders. With the advent of AI learned on data, one can imagine that such rights can extent to requests for forgetting knowledge of patient's data within AI models. However, forgetting patients' imaging data from AI models, is still an under-explored problem. In this paper, we study the influence of patient data on model performance and formulate two hypotheses for a patient's data: either they are common and similar to other patients or form edge cases, i.e. unique and rare cases. We show that it is not possible to easily forget patient data. We propose a targeted forgetting approach to perform patient-wise forgetting. Extensive experiments on the benchmark Automated Cardiac Diagnosis Challenge dataset showcase the improved performance of the proposed targeted forgetting approach as opposed to a state-of-the-art method.

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。

↑