Privacy in Multimodal Federated Human Activity Recognition-猫眼课题宝

DOI：

10.48550/arxiv.2305.12134

发表时间：

2023-05

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Alexandru Iacob;Pedro Gusmão;N. Lane;Armand K. Koupai;M. J. Bocus;Raúl Santos-Rodríguez;R. Piechocki;Ryan McConville

人类活动识别（HAR）训练数据通常是隐私敏感的或由非合作实体持有。联邦学习（FL）通过在边缘客户端上训练ML模型来解决这些问题。这项工作研究了在用户，环境和传感器级别的联邦HAR的隐私的影响。我们表明，FL的HAR的性能取决于假设的隐私级别的FL系统，主要是从不同的传感器的数据托管。通过避免数据共享并假设人类或环境级别的隐私，正如先前的工作所做的那样，准确性降低了5- 7%。然而，将其扩展到模态级别并严格分离多个客户端之间的传感器数据可能会使准确性降低19- 42%。由于这种形式的隐私对于HAR中被动传感方法的道德利用是必要的，我们实现了一个系统，客户端相互训练通用FL模型和每个模态的组级模型。我们的评估表明，这种方法只会导致7-13%的准确性下降，使人们有可能建立不同的硬件HAR系统。

Human Activity Recognition (HAR) training data is often privacy-sensitive or held by non-cooperative entities. Federated Learning (FL) addresses such concerns by training ML models on edge clients. This work studies the impact of privacy in federated HAR at a user, environment, and sensor level. We show that the performance of FL for HAR depends on the assumed privacy level of the FL system and primarily upon the colocation of data from different sensors. By avoiding data sharing and assuming privacy at the human or environment level, as prior works have done, the accuracy decreases by 5-7%. However, extending this to the modality level and strictly separating sensor data between multiple clients may decrease the accuracy by 19-42%. As this form of privacy is necessary for the ethical utilisation of passive sensing methods in HAR, we implement a system where clients mutually train both a general FL model and a group-level one per modality. Our evaluation shows that this method leads to only a 7-13% decrease in accuracy, making it possible to build HAR systems with diverse hardware.

Privacy in Multimodal Federated Human Activity Recognition

文献摘要

相似文献