Privacy-Enhancing Fall Detection from Remote Sensor Data Using Multi-Party Computation

Abstract

Motion-based fall detection systems are concerned with detecting falls from vulnerable users, which is typically performed by classifying measurements from a body-worn inertial measurement unit (IMU) using machine learning. Such systems, however, necessitate the collection of high-resolution measurements that may violate users' privacy, such as revealing their gait, activities of daily living (ADLs), and relative position using dead reckoning. In this paper, we investigate the application of multi-party computation (MPC) to IMU-based fall detection for protecting device measurement confidentiality. Our system is evaluated in a cloud-based setting that precludes parties from learning the underlying data using multiple, disparate cloud instances deployed in three geographical configurations. Using a publicly-available dataset, we demonstrate that MPC-based fall detection from IMU measurements is practical while achieving state-of-the-art error rates. In the best case, our system executes in 365.2 milliseconds, which falls well within the required time window for on-device data acquisition (750ms). CCS CONCEPTS• Security and privacy → Security services; Distributed systems security; Domain-specific security and privacy architectures; • Computer systems organization → Cloud computing.

High Performance Privacy Preserving AI

“…In that process, the server might learn revealing information about the user such as gait, activities and relative position. To move towards a privacy-preserving approach for fall detection [131], investigates an MPC-based fall detection technique based on various AI techniques to detect falls by using data from an IMU sensor. Using publicly available datasets provided by SmartFall [132], they achieve state-of-the-art error rates with their SVM classifier with their derivative-based features.…”

GPS-based fall detection system for old and specially-abled people

“…Yacchirema et al [30] introduced a system that includes a smart IoT gateway for fall detection in the fog and makes use of cloud services to build and deploy a machine learning-based categorization model. Lastly, Mainali and Shepard [31] focused on inertial measurement unit (IMU)-based fall detection using cloud-based multi-party computation (MPC). However, preserving the secrecy of IMU data is the prime objective.…”