C-AAE: Compressively Anonymizing Autoencoders for Privacy-Preserving Activity Recognition in Healthcare Sensor Streams

TL;DR

C-AAE is a novel autoencoder-based method that enhances privacy in healthcare sensor data by reducing re-identification risk and data volume while maintaining activity recognition accuracy.

Contribution

The paper introduces C-AAE, combining an anonymizing autoencoder with adaptive differential pulse-code modulation to improve privacy and data efficiency in sensor-based activity recognition.

Findings

Reduces user re-identification F1 scores by 10-15 points.

Maintains activity recognition F1 within 5 points of baseline.

Decreases data volume by approximately 75%.

Abstract

Wearable accelerometers and gyroscopes encode fine-grained behavioural signatures that can be exploited to re-identify users, making privacy protection essential for healthcare applications. We introduce C-AAE, a compressive anonymizing autoencoder that marries an Anonymizing AutoEncoder (AAE) with Adaptive Differential Pulse-Code Modulation (ADPCM). The AAE first projects raw sensor windows into a latent space that retains activity-relevant features while suppressing identity cues. ADPCM then differentially encodes this latent stream, further masking residual identity information and shrinking the bitrate. Experiments on the MotionSense and PAMAP2 datasets show that C-AAE cuts user re-identification F1 scores by 10-15 percentage points relative to AAE alone, while keeping activity-recognition F1 within 5 percentage points of the unprotected baseline. ADPCM also reduces data volume by roughly 75 %, easing transmission and storage overheads. These results demonstrate that C-AAE offers a practical route to balancing privacy and utility in continuous, sensor-based activity recognition for healthcare.