Treadmill attack on gait-based authentication systems

Rajesh Kumar, Vir Phoha, Anshumali Jain

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper, we demonstrate that gait patterns of an individual captured through a smartphone accelerometer can be imitated with the support of a digital treadmill. Furthermore, we design an attack for a baseline gait based authentication system (GBAS) and rigorously test its performance over an eighteen user data-set. By employing only two imitators and using a simple digital treadmill with speed control functionality, the attack increases the average false acceptance rate (FAR) from 5.8% to 43.66% for random forest, the best performing classifier in our experiments. More specifically, the FAR of eleven out of eighteen users increased to 70% or more. Our results call for a revisit of the design of the GBAS to make them resilient to such attacks.

Original languageEnglish (US)
Title of host publication2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479987764
DOIs
StatePublished - Dec 16 2015
Event7th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2015 - Arlington, United States
Duration: Sep 8 2015Sep 11 2015

Other

Other7th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2015
CountryUnited States
CityArlington
Period9/8/159/11/15

Fingerprint

Exercise equipment
Gait
Authentication
Attack
Smartphones
Speed control
Accelerometers
Classifiers
Speed Control
Random Forest
Performance Test
Accelerometer
Baseline
Classifier
Experiments
Demonstrate
Experiment
False
Design

ASJC Scopus subject areas

  • Statistics and Probability
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Kumar, R., Phoha, V., & Jain, A. (2015). Treadmill attack on gait-based authentication systems. In 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015 [7358801] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BTAS.2015.7358801

Treadmill attack on gait-based authentication systems. / Kumar, Rajesh; Phoha, Vir; Jain, Anshumali.

2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7358801.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kumar, R, Phoha, V & Jain, A 2015, Treadmill attack on gait-based authentication systems. in 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015., 7358801, Institute of Electrical and Electronics Engineers Inc., 7th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2015, Arlington, United States, 9/8/15. https://doi.org/10.1109/BTAS.2015.7358801
Kumar R, Phoha V, Jain A. Treadmill attack on gait-based authentication systems. In 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7358801 https://doi.org/10.1109/BTAS.2015.7358801
Kumar, Rajesh ; Phoha, Vir ; Jain, Anshumali. / Treadmill attack on gait-based authentication systems. 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{24c9507cbaab4ec2869710cc89cca004,
title = "Treadmill attack on gait-based authentication systems",
abstract = "In this paper, we demonstrate that gait patterns of an individual captured through a smartphone accelerometer can be imitated with the support of a digital treadmill. Furthermore, we design an attack for a baseline gait based authentication system (GBAS) and rigorously test its performance over an eighteen user data-set. By employing only two imitators and using a simple digital treadmill with speed control functionality, the attack increases the average false acceptance rate (FAR) from 5.8{\%} to 43.66{\%} for random forest, the best performing classifier in our experiments. More specifically, the FAR of eleven out of eighteen users increased to 70{\%} or more. Our results call for a revisit of the design of the GBAS to make them resilient to such attacks.",
author = "Rajesh Kumar and Vir Phoha and Anshumali Jain",
year = "2015",
month = "12",
day = "16",
doi = "10.1109/BTAS.2015.7358801",
language = "English (US)",
isbn = "9781479987764",
booktitle = "2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Treadmill attack on gait-based authentication systems

AU - Kumar, Rajesh

AU - Phoha, Vir

AU - Jain, Anshumali

PY - 2015/12/16

Y1 - 2015/12/16

N2 - In this paper, we demonstrate that gait patterns of an individual captured through a smartphone accelerometer can be imitated with the support of a digital treadmill. Furthermore, we design an attack for a baseline gait based authentication system (GBAS) and rigorously test its performance over an eighteen user data-set. By employing only two imitators and using a simple digital treadmill with speed control functionality, the attack increases the average false acceptance rate (FAR) from 5.8% to 43.66% for random forest, the best performing classifier in our experiments. More specifically, the FAR of eleven out of eighteen users increased to 70% or more. Our results call for a revisit of the design of the GBAS to make them resilient to such attacks.

AB - In this paper, we demonstrate that gait patterns of an individual captured through a smartphone accelerometer can be imitated with the support of a digital treadmill. Furthermore, we design an attack for a baseline gait based authentication system (GBAS) and rigorously test its performance over an eighteen user data-set. By employing only two imitators and using a simple digital treadmill with speed control functionality, the attack increases the average false acceptance rate (FAR) from 5.8% to 43.66% for random forest, the best performing classifier in our experiments. More specifically, the FAR of eleven out of eighteen users increased to 70% or more. Our results call for a revisit of the design of the GBAS to make them resilient to such attacks.

UR - http://www.scopus.com/inward/record.url?scp=84962875954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962875954&partnerID=8YFLogxK

U2 - 10.1109/BTAS.2015.7358801

DO - 10.1109/BTAS.2015.7358801

M3 - Conference contribution

SN - 9781479987764

BT - 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -