E-BIAS: A pervasive EEG-based identification and authentication system

Javad Sohankar, Koosha Sadeghi, Ayan Banerjee, Sandeep Gupta

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

20 Citations (Scopus)

Abstract

Security systems using brain signals or Electroencephalography (EEG), is an emerging field of research. Brain signal characteristics such as chaotic nature and uniqueness, make it an appropriate information source to be used in security systems. In this paper, E-BIAS, a pervasive EEG-based security system with both identification and authentication functionalities is developed. The main challenges are: 1) accuracy, 2) timeliness, 3) energy efficiency, 4) usability, and 5) robustness. Therefore, we apply Machine Learning (ML) algorithms with low training times, multi-tier distributed computing architecture, and commercial single channel dry electrode wireless EEG headsets to respectively overcome the first four challenges. With only two minutes of training time and a simple rest task, the authentication and identification performance reaches 95% and 80%, respectively on 10 subjects. We finally test the robustness of our EEG-based seamless security system against three types of attacks: a) brain impersonation, b) database hacking, and c) communication snooping and discuss the system configurations which can avoid data leakage.

Original languageEnglish (US)
Title of host publicationQ2SWinet 2015 - Proceedings of the 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks
PublisherAssociation for Computing Machinery, Inc
Pages165-172
Number of pages8
ISBN (Print)9781450337571
DOIs
StatePublished - Nov 2 2015
Event11th ACM Symposium on QoS and Security for Wireless and Mobile Networks, Q2SWinet 2015 - Cancun, Mexico
Duration: Nov 2 2015Nov 6 2015

Other

Other11th ACM Symposium on QoS and Security for Wireless and Mobile Networks, Q2SWinet 2015
CountryMexico
CityCancun
Period11/2/1511/6/15

Fingerprint

Electroencephalography
Security systems
Authentication
Brain
Distributed computer systems
Learning algorithms
Energy efficiency
Learning systems
Electrodes
Communication

Keywords

  • Electroencephalogram
  • Pervasive security systems

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Sohankar, J., Sadeghi, K., Banerjee, A., & Gupta, S. (2015). E-BIAS: A pervasive EEG-based identification and authentication system. In Q2SWinet 2015 - Proceedings of the 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks (pp. 165-172). Association for Computing Machinery, Inc. https://doi.org/10.1145/2815317.2815341

E-BIAS : A pervasive EEG-based identification and authentication system. / Sohankar, Javad; Sadeghi, Koosha; Banerjee, Ayan; Gupta, Sandeep.

Q2SWinet 2015 - Proceedings of the 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks. Association for Computing Machinery, Inc, 2015. p. 165-172.

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

Sohankar, J, Sadeghi, K, Banerjee, A & Gupta, S 2015, E-BIAS: A pervasive EEG-based identification and authentication system. in Q2SWinet 2015 - Proceedings of the 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks. Association for Computing Machinery, Inc, pp. 165-172, 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks, Q2SWinet 2015, Cancun, Mexico, 11/2/15. https://doi.org/10.1145/2815317.2815341
Sohankar J, Sadeghi K, Banerjee A, Gupta S. E-BIAS: A pervasive EEG-based identification and authentication system. In Q2SWinet 2015 - Proceedings of the 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks. Association for Computing Machinery, Inc. 2015. p. 165-172 https://doi.org/10.1145/2815317.2815341
Sohankar, Javad ; Sadeghi, Koosha ; Banerjee, Ayan ; Gupta, Sandeep. / E-BIAS : A pervasive EEG-based identification and authentication system. Q2SWinet 2015 - Proceedings of the 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks. Association for Computing Machinery, Inc, 2015. pp. 165-172
@inproceedings{79ea6a2f2b154daa99af2bae41560440,
title = "E-BIAS: A pervasive EEG-based identification and authentication system",
abstract = "Security systems using brain signals or Electroencephalography (EEG), is an emerging field of research. Brain signal characteristics such as chaotic nature and uniqueness, make it an appropriate information source to be used in security systems. In this paper, E-BIAS, a pervasive EEG-based security system with both identification and authentication functionalities is developed. The main challenges are: 1) accuracy, 2) timeliness, 3) energy efficiency, 4) usability, and 5) robustness. Therefore, we apply Machine Learning (ML) algorithms with low training times, multi-tier distributed computing architecture, and commercial single channel dry electrode wireless EEG headsets to respectively overcome the first four challenges. With only two minutes of training time and a simple rest task, the authentication and identification performance reaches 95{\%} and 80{\%}, respectively on 10 subjects. We finally test the robustness of our EEG-based seamless security system against three types of attacks: a) brain impersonation, b) database hacking, and c) communication snooping and discuss the system configurations which can avoid data leakage.",
keywords = "Electroencephalogram, Pervasive security systems",
author = "Javad Sohankar and Koosha Sadeghi and Ayan Banerjee and Sandeep Gupta",
year = "2015",
month = "11",
day = "2",
doi = "10.1145/2815317.2815341",
language = "English (US)",
isbn = "9781450337571",
pages = "165--172",
booktitle = "Q2SWinet 2015 - Proceedings of the 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - E-BIAS

T2 - A pervasive EEG-based identification and authentication system

AU - Sohankar, Javad

AU - Sadeghi, Koosha

AU - Banerjee, Ayan

AU - Gupta, Sandeep

PY - 2015/11/2

Y1 - 2015/11/2

N2 - Security systems using brain signals or Electroencephalography (EEG), is an emerging field of research. Brain signal characteristics such as chaotic nature and uniqueness, make it an appropriate information source to be used in security systems. In this paper, E-BIAS, a pervasive EEG-based security system with both identification and authentication functionalities is developed. The main challenges are: 1) accuracy, 2) timeliness, 3) energy efficiency, 4) usability, and 5) robustness. Therefore, we apply Machine Learning (ML) algorithms with low training times, multi-tier distributed computing architecture, and commercial single channel dry electrode wireless EEG headsets to respectively overcome the first four challenges. With only two minutes of training time and a simple rest task, the authentication and identification performance reaches 95% and 80%, respectively on 10 subjects. We finally test the robustness of our EEG-based seamless security system against three types of attacks: a) brain impersonation, b) database hacking, and c) communication snooping and discuss the system configurations which can avoid data leakage.

AB - Security systems using brain signals or Electroencephalography (EEG), is an emerging field of research. Brain signal characteristics such as chaotic nature and uniqueness, make it an appropriate information source to be used in security systems. In this paper, E-BIAS, a pervasive EEG-based security system with both identification and authentication functionalities is developed. The main challenges are: 1) accuracy, 2) timeliness, 3) energy efficiency, 4) usability, and 5) robustness. Therefore, we apply Machine Learning (ML) algorithms with low training times, multi-tier distributed computing architecture, and commercial single channel dry electrode wireless EEG headsets to respectively overcome the first four challenges. With only two minutes of training time and a simple rest task, the authentication and identification performance reaches 95% and 80%, respectively on 10 subjects. We finally test the robustness of our EEG-based seamless security system against three types of attacks: a) brain impersonation, b) database hacking, and c) communication snooping and discuss the system configurations which can avoid data leakage.

KW - Electroencephalogram

KW - Pervasive security systems

UR - http://www.scopus.com/inward/record.url?scp=84958535715&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958535715&partnerID=8YFLogxK

U2 - 10.1145/2815317.2815341

DO - 10.1145/2815317.2815341

M3 - Conference contribution

AN - SCOPUS:84958535715

SN - 9781450337571

SP - 165

EP - 172

BT - Q2SWinet 2015 - Proceedings of the 11th ACM Symposium on QoS and Security for Wireless and Mobile Networks

PB - Association for Computing Machinery, Inc

ER -