arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.08605cs.NIcs.LG
收藏

重新训练ML模型以用于边缘的IoT设备识别的案例

The Case for Retraining of ML Models for IoT Device Identification at the Edge

Imperial College London(帝国理工学院);University of Cambridge(剑桥大学);University of York(约克大学)

Roman Kolcun, Diana Andreea Popescu, Vadim Safronov, Poonam Yadav, Anna Maria Mandalari, Yiming Xie, Richard Mortier, Hamed Haddadi

摘要:

众所周知,物联网(IoT)设备是许多安全问题的根源,因此它们将从自动化管理中受益匪浅。这就需要对设备进行可靠的识别,以便应用适当的网络安全策略。我们通过探索如何使用网络边缘可用的资源,根据物联网设备的网络行为准确识别物联网设备来应对这一挑战。在本文中,我们比较了五种不同的机器学习模型(基于树的和基于神经网络的)的准确性,通过使用来自大型物联网测试床的数据包跟踪数据来识别物联网设备,表明所有模型都需要随着时间的推移进行更新,以避免准确性的显著下降。为了有效地更新模型,我们发现有必要使用从部署环境收集的数据,例如,家庭。因此,我们使用代表网络边缘可用的硬件资源和数据源来评估我们的方法,例如在物联网部署中。我们表明,在边缘更新基于神经网络的模型是可行的,因为它们需要较低的计算和内存资源,并且它们的结构易于更新。我们的研究结果表明,它是有可能实现设备识别和分类,分别超过80%和90%的准确率在边缘。

英文摘要:

Internet-of-Things (IoT) devices are known to be the source of many security problems, and as such they would greatly benefit from automated management. This requires robustly identifying devices so that appropriate network security policies can be applied. We address this challenge by exploring how to accurately identify IoT devices based on their network behavior, using resources available at the edge of the network. In this paper, we compare the accuracy of five different machine learning models (tree-based and neural network-based) for identifying IoT devices by using packet trace data from a large IoT test-bed, showing that all models need to be updated over time to avoid significant degradation in accuracy. In order to effectively update the models, we find that it is necessary to use data gathered from the deployment environment, e.g., the household. We therefore evaluate our approach using hardware resources and data sources representative of those that would be available at the edge of the network, such as in an IoT deployment. We show that updating neural network-based models at the edge is feasible, as they require low computational and memory resources and their structure is amenable to being updated. Our results show that it is possible to achieve device identification and categorization with over 80% and 90% accuracy respectively at the edge.

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。

↑