WristPrint: Guided Tutorial

About the Tutorial:

Wearable, body-worn sensors can provide a richness of real-time, real-world physiological and contextual data that offers unprecedented insights to help people and advance research to improve health and well-being. This same richness of physiological and bio-behavioral data also presents ever-evolving privacy risks. Growing research demonstrates how wrist-worn sensors can do just that – offer remarkable health and behavioral insight but also collect information that is identifiable to an individual. This includes raw data streams that have historically been considered de-identified.

This self-paced guided tutorial explores the following learning objectives:
• Understand re-identification risks from raw accelerometer data,
• identify factors influencing these risks, and
• learn strategies to mitigate risks while preserving research utility.

Using real-world examples and scenarios extracted from the literature, we hope this learning module will help you and the research community to better understand these emerging risks and ways to turn awareness into action. Using this knowledge will help researchers continue unlocking the remarkable potential of wrist-worn sensor data while protecting individuals’ privacy.

About the Award:

Grant #: 3P41EB028242-04S1
PI: Dr. Santosh Kumar, The University of Memphis
Team: Dr. Camille Nebeker, UCSD; Shahin Samiei, The University of Memphis
Publications:

• Nazir Saleheen, Md Azim Ullah, Supriyo Chakraborty, Deniz S. Ones, Mani Srivastava, and Santosh Kumar. 2021. WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data. In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security (CCS ’21). Association for Computing Machinery, New York, NY, USA, 2807–2823. https://doi.org/10.1145/3460120.3484799.