arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2401.08458cs.CRcs.AI
收藏

数字医疗中联邦学习的安全与隐私问题及解决方案

Security and Privacy Issues and Solutions in Federated Learning for Digital Healthcare

Sungkyunkwan University(成均馆大学)

Hyejun Jeong, Tai-Myoung Chung

AI总结:

本文针对数字医疗中联邦学习因服务器与客户端多轮通信而扩大的攻击面,系统梳理其脆弱性、攻击方式与防御方案,并指出未来构建更鲁棒联邦学习的研究方向。

摘要:

联邦学习的出现使得构建一个高性能模型成为可能,如同该模型是在大量数据上训练而成。众多参与方与一个服务器协同训练模型,而无需披露或收集数据。医疗行业对安全与隐私的要求极为严格,由于严格的数据政策使得数据收集不再可行,因此该行业能够从这一新型学习范式中显著受益。尽管如此,尚未解决的挑战以及攻击缓解措施不足正阻碍其推广应用。攻击面与传统集中式学习不同,因为服务器与客户端在每一轮训练之间都会进行通信。因此,在本文中,我们基于扩大的攻击面呈现了脆弱性、攻击与防御手段,并针对构建更鲁棒的联邦学习提出了有前景的新研究方向。

英文摘要:

The advent of Federated Learning has enabled the creation of a high-performing model as if it had been trained on a considerable amount of data. A multitude of participants and a server cooperatively train a model without the need for data disclosure or collection. The healthcare industry, where security and privacy are paramount, can substantially benefit from this new learning paradigm, as data collection is no longer feasible due to stringent data policies. Nonetheless, unaddressed challenges and insufficient attack mitigation are hampering its adoption. Attack surfaces differ from traditional centralized learning in that the server and clients communicate between each round of training. In this paper, we thus present vulnerabilities, attacks, and defenses based on the widened attack surfaces, as well as suggest promising new research directions toward a more robust FL.

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。

↑