iBranchy: An Accelerated Edge Inference Platform for loT Devices◊
iBranchy: An Accelerated Edge Inference Platform for loT Devices◊
复制标题
iBranchy：物联网设备的加速边缘推理平台◊
DOI：
10.1145/3453142.3493517
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
T. Nadeem
中科院分区：
文献类型：
--
作者：
S. Nukavarapu;Mohammed Ayyat;T. Nadeem
随着网络边缘物联网设备的惊人增长，出现了许多新的应用，包括远程健康监控、增强现实和视频分析。然而，使这些设备免受不同的网络攻击仍然是一个重大挑战。为了为物联网设备提供更安全的服务，必须在网络边缘快速发现威胁，并在设备资源限制范围内有效处理威胁。深度神经网络（DNN）已经成为提供安全性和高性能的解决方案。然而，现有的基于边缘的物联网DNN分类器既不轻量级也不灵活，无法基于设备类型执行条件计算以节省边缘资源。动态深度神经网络最近成为一种技术，可以通过执行条件计算来加速推理，从而节省计算资源。在这项工作中，我们设计和开发了一个基于动态神经网络的加速物联网分类器iBranchy，它可以用更少的边缘资源进行快速推理，同时还提供了适应不同硬件和网络条件的灵活性。CCS概念·安全和隐私→移动的和无线安全; ·计算方法→神经网络。
With the phenomenal growth of IoT devices at the network edge, many new applications have emerged, including remote health monitoring, augmented reality, and video analytics. However, se-curing these devices from different network attacks has remained a major challenge. To enable more secure services for IoT devices, threats must be discovered quickly in the network edge and effi-ciently dealt with within device resource constraints. Deep Neural Networks (DNN) have emerged as solution to provide both security and high performance. However, existing edge-based IoT DNN clas-sifiers are neither lightweight nor flexible to perform conditional computation based on device types to save edge resources. Dynamic deep neural networks have recently emerged as a technique that can accelerate inference by performing conditional computation and, therefore, save computational resources. In this work, we de-sign and develop an accelerated IoT classifier iBranchy based on a dynamic neural network that can perform quick inference with fewer edge resources while also providing flexibility to adapt to different hardware and network conditions. CCS CONCEPTS • Security and privacy → Mobile and wireless security; • Com-puting methodologies → Neural networks.
DOI：
10.1109/sec50012.2020.00014
发表时间：
2020-11
期刊：
2020 IEEE/ACM Symposium on Edge Computing (SEC)
影响因子：
--
作者：
Biyi Fang;Xiao Zeng;Faen Zhang;Hui Xu;Mi Zhang
通讯作者：
Biyi Fang;Xiao Zeng;Faen Zhang;Hui Xu;Mi Zhang