Personalized Privacy Assistants for the Internet of Things Providing Users with Notice and Choice
Personalized Privacy Assistants for the Internet of Things Providing Users with Notice and Choice
复制标题
DOI：
10.1109/mprv.2018.03367733
复制
发表时间：
2018-07-01
影响因子：
1.6
通讯作者：
Sadeh, Norman
中科院分区：
文献类型：
--
作者：
Das, Anupam;Degeling, Martin;Sadeh, Norman
随着我们与越来越多样化的传感技术进行交互，我们很难跟上收集和使用我们自己数据的许多不同方式。一项又一项研究表明，尽管人们普遍关心自己的隐私，但他们觉得自己对收集和使用自己的数据几乎没有意识，更不用说控制了。本文总结了正在进行的研究，以开发和现场隐私助手，旨在使人们能够重新控制他们在物联网（IoT）中的隐私。具体来说，我们专注于我们开发和部署的基础设施，以支持物联网的隐私助理。该基础设施使助手能够发现其用户附近的物联网资源（传感器，应用程序，服务，设备等），并有选择地向用户告知与这些资源相关的数据实践。它还支持发现物联网资源的用户可配置设置（选择加入、选择退出、数据擦除等），使隐私助手能够帮助用户根据他们的隐私期望配置他们的物联网体验。我们还讨论了如何使用机器学习来构建和完善用户隐私期望和偏好的模型，我们计划开发个性化的隐私助理，能够有选择地向用户告知他们实际关心的数据实践，并帮助他们配置相关的隐私设置。
As we interact with an increasingly diverse set of sensing technologies, it becomes difficult to keep up with the many different ways in which data about ourselves is collected and used. Study after study has shown that while people generally care about their privacy, they feel they have little awareness of-let alone control over-the collection and use of their data. This article summarizes ongoing research to develop and field privacy assistants designed to empower people to regain control over their privacy in the Internet of Things (IoT). Specifically, we focus on the infrastructure we have developed and deployed to support privacy assistants for the IoT. This infrastructure enables the assistants to discover IoT resources (sensors, apps, services, devices, and so on) in the vicinity of their users, and selectively inform users about the data practices associated with these resources. It also supports the discovery of userconfigurable settings for IoT resources (opt in, opt out, data erasure, and so on) if there are any, enabling privacy assistants to help users configure their IoT experience in accordance with their privacy expectations. We also discuss how, using machine learning to build and refine models of users' privacy expectations and preferences, we plan to developed personalized privacy assistants capable of selectively informing their users about the data practices they actually care about and of helping them configure associated privacy settings.