| 摘要: |
| 万物互联时代，物联网中感知设备持续产生大量的敏感数据。实时且安全的数据流处理是面向物联网关键应用中需要解决的一个挑战。在近年兴起的边缘计算模式下，借助靠近终端的设备执行计算密集型任务与存储大量的终端设备数据，物联网中数据流处理的安全性和实时性可以得到有效的提升。然而，在基于边缘的物联网流处理架构下，数据被暴露在边缘设备易受攻击的软件堆栈中，从而给边缘带来了新的安全威胁。为此，文章对基于可信执行环境的物联网边缘流处理安全技术进行研究。从边缘出发，介绍边缘安全流处理相关背景并探讨边缘安全流处理的具体解决方案，接着分析主流方案的实验结果，最后展望未来研究方向。 |
| 关键词: 物联网 边缘计算 可信执行环境 安全流处理 |
| DOI：10.19363/J.cnki.cn10-1380/tn.2021.05.11 |
| 投稿时间：2020-07-24修订日期：2020-12-30 |
| 基金项目:本课题得到广东省重点研发计划（No.2018B010113001），之江实验室科研项目（先进工业互联网安全平台），上海市扬帆计划（No.20YF1413700）资助。 |
|
| Survey of Security Technologies for IoT Edge Stream Processing Based on Trusted Execution Environment |
| JIANG Chao,LI Yufeng,CAO Chenhong,LI Jiangtao |
| College of Computer Engineering and Science, Shanghai Univesity, Shanghai 200444, China;College of Computer Engineering and Science, Shanghai Univesity, Shanghai 200444, China;Network Communication and Security Purple Mountain Laboratory, Nanjing 211100, China |
| Abstract: |
| In the era of the Internet of Everything, sensing devices in the Internet of Things continue to generate a large amount of sensitive data. The processing of real-time and secure data stream is a challenge that needs to be solved in key applications facing the Internet of Things. In the edge computing model that has emerged in recent years, with the help of devices close to the terminal to perform computationally intensive tasks and store a large amount of terminal device data, the security and real-time performance of data stream processing in the Internet of Things can be effectively improved. However, under the edge-based IoT stream processing architecture, data is exposed to the vulnerable software stack of the edge device, which brings new security threats to the edge. To this end, the article studies the security technology of IoT edge stream processing based on trusted execution environment. Starting from the edge, we first introduce the relevant background of secure edge stream processing, then discuss the specific scheme of edge stream processing and analyze the experimental results of the mainstream scheme, and finally look forward to the future research direction. |
| Key words: Internet of Things edge computing trusted execution environment secure stream processing |
