Privacy and Utility Preserving Sensor-Data Transformations
This addresses privacy concerns for users of wearable devices by preventing sensitive inferences and re-identification with minimal impact on application performance, though it is incremental in applying known privacy techniques to sensor data.
The paper tackles privacy threats from sharing raw sensor data by proposing transformations that eliminate patterns for user re-identification and sensitive activity inference, while maintaining utility for non-sensitive tasks with less than 5 percentage points accuracy loss.
Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mechanisms to transform sensor data before sharing them with applications running on users' devices. These transformations aim at eliminating patterns that can be used for user re-identification or for inferring potentially sensitive activities, while introducing a minor utility loss for the target application (or task). We show that, on gesture and activity recognition tasks, we can prevent inference of potentially sensitive activities while keeping the reduction in recognition accuracy of non-sensitive activities to less than 5 percentage points. We also show that we can reduce the accuracy of user re-identification and of the potential inference of gender to the level of a random guess, while keeping the accuracy of activity recognition comparable to that obtained on the original data.