AI RESEARCH

Class-Aware Adaptive Differential Privacy in Deep Learning for Sensor-Based Fall Detection

arXiv CS.LG

ArXi:2605.01679v1 Announce Type: cross Fall detection is a critical task in healthcare, particularly for elderly people. Timely fall detection and treatment can prevent severe injuries. Sensor-based activity data can be used to detect fall. However, this data are highly sensitive and raises significant privacy concerns. Existing privacy approaches apply uniform noise across all