Emerging Privacy Challenges and Approaches in CAV Systems
Emerging Privacy Challenges and Approaches in CAV Systems
复制标题
DOI：
10.1049/cp.2019.0141
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
U. Atmaca;Carsten Maple;M. Dianati
中科院分区：
文献类型：
--
作者：
U. Atmaca;Carsten Maple;M. Dianati
互联网连接设备、互联网服务和物联网系统的增长持续快速，它们在运输系统中的应用预示着游戏规则的改变。许多正在开发的CAV（互联和自动驾驶汽车）功能，例如交通规划、优化、管理、安全关键和协作自动驾驶应用程序，都依赖于来自各种来源的数据。这些功能的功效在很大程度上取决于共享数据的维度、数量和准确性。一般来说，它认为可用的数据量越大，功能的功效就越大。然而，这些数据中有许多是隐私敏感的，包括个人、商业和研究数据。位置数据及其与身份和时间数据的相关性可以帮助推断其他个人信息，例如家庭/工作地点，年龄，工作，行为特征，习惯，社会关系。这项工作对CAV系统的新兴隐私挑战和解决方案进行了分类，并确定了未来研究的知识差距，这将最大限度地减少和减轻隐私问题，而不会影响功能的有效性。
The growth of Internet-connected devices, Internet-enabled services and Internet of Things systems continues at a rapid pace, and their application to transport systems is heralded as game-changing. Numerous developing CAV (Connected and Autonomous Vehicle) functions, such as traffic planning, optimisation, management, safety-critical and cooperative autonomous driving applications, rely on data from various sources. The efficacy of these functions is highly dependent on the dimensionality, amount and accuracy of the data being shared. It holds, in general, that the greater the amount of data available, the greater the efficacy of the function. However, much of this data is privacy-sensitive, including personal, commercial and research data. Location data and its correlation with identity and temporal data can help infer other personal information, such as home/work locations, age, job, behavioural features, habits, social relationships. This work categorises the emerging privacy challenges and solutions for CAV systems and identifies the knowledge gap for future research, which will minimise and mitigate privacy concerns without hampering the efficacy of the functions.