WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data

Nazir Saleheen; Md Azim Ullah; Supriyo Chakraborty; Deniz S. Ones; Mani Srivastava; Santosh Kumar

doi:10.1145/3460120.3484799

WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data

Nazir Saleheen, Md Azim Ullah, Supriyo Chakraborty, Deniz S. Ones, Mani Srivastava, Santosh Kumar

Psychology (Twin Cities)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

Public release of wrist-worn motion sensor data is growing. They enable and accelerate research in developing new algorithms to passively track daily activities, resulting in improved health and wellness utilities of smartwatches and activity trackers. But, when combined with sensitive attribute inference attack and linkage attack via re-identification of the same user in multiple datasets, undisclosed sensitive attributes can be revealed to unintended organizations with potentially adverse consequences for unsuspecting data contributing users. To guide both users and data collecting researchers, we characterize the re-identification risks inherent in motion sensor data collected from wrist-worn devices in users' natural environment. For this purpose, we use an open-set formulation, train a deep learning architecture with a new loss function, and apply our model to a new data set consisting of 10 weeks of daily sensor wearing by 353 users. We find that re-identification risk increases with an increase in the activity intensity. On average, such risk is 96% for a user when sharing a full day of sensor data.

Original language	English (US)
Title of host publication	CCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security
Publisher	Association for Computing Machinery
Pages	2807-2823
Number of pages	17
ISBN (Electronic)	9781450384544
DOIs	https://doi.org/10.1145/3460120.3484799
State	Published - Nov 12 2021
Event	27th ACM Annual Conference on Computer and Communication Security, CCS 2021 - Virtual, Online, Korea, Republic of Duration: Nov 15 2021 → Nov 19 2021

Publication series

Name	Proceedings of the ACM Conference on Computer and Communications Security
ISSN (Print)	1543-7221

Conference

Conference	27th ACM Annual Conference on Computer and Communication Security, CCS 2021
Country/Territory	Korea, Republic of
City	Virtual, Online
Period	11/15/21 → 11/19/21

Bibliographical note

Funding Information:
This research was supported in part by the National Institutes of Health (NIH) under award P41EB028242, by the National Science Foundation (NSF) under awards ACI-1640813, CNS-1823221, CNS-1705135, and CNS-1822935, and by the Combat Capabilities Development Command (DEVCOM), Army Research Laboratory (ARL) under Cooperative Agreement Number W911NF-13-2-0045 (ARL Cyber Security CRA). The mPerf research study was supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA Contract No. 2017-17042800006. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of ODNI, IARPA, DEVCOM, ARL, NSF, NIH, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes not withstanding any copyright notation therein.

Publisher Copyright:
© 2021 ACM.

Keywords

privacy
re-identification risk
user re-identification
wrist-worn accelerometers

Publisher link

10.1145/3460120.3484799

Find It

Find It at U of M Libraries

Cite this

Saleheen, N., Ullah, M. A., Chakraborty, S., Ones, D. S., Srivastava, M., & Kumar, S. (2021). WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data. In CCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security (pp. 2807-2823). (Proceedings of the ACM Conference on Computer and Communications Security). Association for Computing Machinery. https://doi.org/10.1145/3460120.3484799

WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data. / Saleheen, Nazir; Ullah, Md Azim; Chakraborty, Supriyo et al.
CCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. Association for Computing Machinery, 2021. p. 2807-2823 (Proceedings of the ACM Conference on Computer and Communications Security).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Saleheen, N, Ullah, MA, Chakraborty, S, Ones, DS, Srivastava, M & Kumar, S 2021, WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data. in CCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. Proceedings of the ACM Conference on Computer and Communications Security, Association for Computing Machinery, pp. 2807-2823, 27th ACM Annual Conference on Computer and Communication Security, CCS 2021, Virtual, Online, Korea, Republic of, 11/15/21. https://doi.org/10.1145/3460120.3484799

Saleheen N, Ullah MA, Chakraborty S, Ones DS, Srivastava M, Kumar S. WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data. In CCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. Association for Computing Machinery. 2021. p. 2807-2823. (Proceedings of the ACM Conference on Computer and Communications Security). doi: 10.1145/3460120.3484799

Saleheen, Nazir ; Ullah, Md Azim ; Chakraborty, Supriyo et al. / WristPrint : Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data. CCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. Association for Computing Machinery, 2021. pp. 2807-2823 (Proceedings of the ACM Conference on Computer and Communications Security).

@inproceedings{91d9106f76314d458fd82e9f97b04e64,

title = "WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data",

abstract = "Public release of wrist-worn motion sensor data is growing. They enable and accelerate research in developing new algorithms to passively track daily activities, resulting in improved health and wellness utilities of smartwatches and activity trackers. But, when combined with sensitive attribute inference attack and linkage attack via re-identification of the same user in multiple datasets, undisclosed sensitive attributes can be revealed to unintended organizations with potentially adverse consequences for unsuspecting data contributing users. To guide both users and data collecting researchers, we characterize the re-identification risks inherent in motion sensor data collected from wrist-worn devices in users' natural environment. For this purpose, we use an open-set formulation, train a deep learning architecture with a new loss function, and apply our model to a new data set consisting of 10 weeks of daily sensor wearing by 353 users. We find that re-identification risk increases with an increase in the activity intensity. On average, such risk is 96% for a user when sharing a full day of sensor data.",

keywords = "privacy, re-identification risk, user re-identification, wrist-worn accelerometers",

author = "Nazir Saleheen and Ullah, {Md Azim} and Supriyo Chakraborty and Ones, {Deniz S.} and Mani Srivastava and Santosh Kumar",

note = "Funding Information: This research was supported in part by the National Institutes of Health (NIH) under award P41EB028242, by the National Science Foundation (NSF) under awards ACI-1640813, CNS-1823221, CNS-1705135, and CNS-1822935, and by the Combat Capabilities Development Command (DEVCOM), Army Research Laboratory (ARL) under Cooperative Agreement Number W911NF-13-2-0045 (ARL Cyber Security CRA). The mPerf research study was supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA Contract No. 2017-17042800006. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of ODNI, IARPA, DEVCOM, ARL, NSF, NIH, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes not withstanding any copyright notation therein. Publisher Copyright: {\textcopyright} 2021 ACM.; 27th ACM Annual Conference on Computer and Communication Security, CCS 2021 ; Conference date: 15-11-2021 Through 19-11-2021",

year = "2021",

month = nov,

day = "12",

doi = "10.1145/3460120.3484799",

language = "English (US)",

series = "Proceedings of the ACM Conference on Computer and Communications Security",

publisher = "Association for Computing Machinery",

pages = "2807--2823",

booktitle = "CCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security",

}

TY - GEN

T1 - WristPrint

T2 - 27th ACM Annual Conference on Computer and Communication Security, CCS 2021

AU - Saleheen, Nazir

AU - Ullah, Md Azim

AU - Chakraborty, Supriyo

AU - Ones, Deniz S.

AU - Srivastava, Mani

AU - Kumar, Santosh

N1 - Funding Information: This research was supported in part by the National Institutes of Health (NIH) under award P41EB028242, by the National Science Foundation (NSF) under awards ACI-1640813, CNS-1823221, CNS-1705135, and CNS-1822935, and by the Combat Capabilities Development Command (DEVCOM), Army Research Laboratory (ARL) under Cooperative Agreement Number W911NF-13-2-0045 (ARL Cyber Security CRA). The mPerf research study was supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA Contract No. 2017-17042800006. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of ODNI, IARPA, DEVCOM, ARL, NSF, NIH, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes not withstanding any copyright notation therein. Publisher Copyright: © 2021 ACM.

PY - 2021/11/12

Y1 - 2021/11/12

N2 - Public release of wrist-worn motion sensor data is growing. They enable and accelerate research in developing new algorithms to passively track daily activities, resulting in improved health and wellness utilities of smartwatches and activity trackers. But, when combined with sensitive attribute inference attack and linkage attack via re-identification of the same user in multiple datasets, undisclosed sensitive attributes can be revealed to unintended organizations with potentially adverse consequences for unsuspecting data contributing users. To guide both users and data collecting researchers, we characterize the re-identification risks inherent in motion sensor data collected from wrist-worn devices in users' natural environment. For this purpose, we use an open-set formulation, train a deep learning architecture with a new loss function, and apply our model to a new data set consisting of 10 weeks of daily sensor wearing by 353 users. We find that re-identification risk increases with an increase in the activity intensity. On average, such risk is 96% for a user when sharing a full day of sensor data.

AB - Public release of wrist-worn motion sensor data is growing. They enable and accelerate research in developing new algorithms to passively track daily activities, resulting in improved health and wellness utilities of smartwatches and activity trackers. But, when combined with sensitive attribute inference attack and linkage attack via re-identification of the same user in multiple datasets, undisclosed sensitive attributes can be revealed to unintended organizations with potentially adverse consequences for unsuspecting data contributing users. To guide both users and data collecting researchers, we characterize the re-identification risks inherent in motion sensor data collected from wrist-worn devices in users' natural environment. For this purpose, we use an open-set formulation, train a deep learning architecture with a new loss function, and apply our model to a new data set consisting of 10 weeks of daily sensor wearing by 353 users. We find that re-identification risk increases with an increase in the activity intensity. On average, such risk is 96% for a user when sharing a full day of sensor data.

KW - privacy

KW - re-identification risk

KW - user re-identification

KW - wrist-worn accelerometers

UR - http://www.scopus.com/inward/record.url?scp=85119334361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85119334361&partnerID=8YFLogxK

U2 - 10.1145/3460120.3484799

DO - 10.1145/3460120.3484799

M3 - Conference contribution

AN - SCOPUS:85119334361

T3 - Proceedings of the ACM Conference on Computer and Communications Security

SP - 2807

EP - 2823

BT - CCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security

PB - Association for Computing Machinery

Y2 - 15 November 2021 through 19 November 2021

ER -

WristPrint: Characterizing User Re-identification Risks from Wrist-worn Accelerometry Data

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this