A novel spoofing attack against electroencephalogram-based security systems

Koosha Sadeghi, Javad Sohankar, Ayan Banerjee, Sandeep Gupta

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

2 Citations (Scopus)

Abstract

Security systems using brain signals or Electroencephalogram (EEG), attempt to exploit chaotic nature of brain signals and their individuality to derive security primitives that are hard to reproduce. In this sense, the signal features are extracted to train a Machine Learning (ML) algorithm for classification. However, although brain signals are chaotic, feature extraction process might reduce the chaos rendering features in a way that they can be generated. Besides, even if features are chaotic, ML techniques might classify them in such a manner that an element in a particular class becomes easy to generate. In this paper, we perform entropy analysis on common features used in EEG-based security systems to estimate their information content, which is used to propose a novel technique for EEG signal generation in feature domain instead of time domain. These generated signals can potentially be used for spoofing attacks. We consider five types of feature extraction techniques and six classifiers found in recently proposed security systems, and analyze their vulnerability to spoofing attacks using generated EEG signals. The results show that the generation scheme can synthesize artificial signals to get classified as genuine brain signals by ML algorithms.

Original languageEnglish (US)
Title of host publication2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
ISBN (Electronic)9781538604342
DOIs
StatePublished - Jun 26 2018
Event2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - San Francisco, United States
Duration: Apr 4 2017Apr 8 2017

Other

Other2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017
CountryUnited States
CitySan Francisco
Period4/4/174/8/17

Fingerprint

Electroencephalography
Security systems
Brain
brain
Learning systems
Learning algorithms
Feature extraction
learning
information content
individuality
chaos
entropy
Chaos theory
vulnerability
Classifiers
Entropy
Attack
Electroencephalogram
chaotic dynamics
train

Keywords

  • electroencephalogram
  • entropy
  • spoofing attack

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Energy Engineering and Power Technology
  • Safety, Risk, Reliability and Quality
  • Urban Studies

Cite this

Sadeghi, K., Sohankar, J., Banerjee, A., & Gupta, S. (2018). A novel spoofing attack against electroencephalogram-based security systems. In 2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings (pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/UIC-ATC.2017.8397607

A novel spoofing attack against electroencephalogram-based security systems. / Sadeghi, Koosha; Sohankar, Javad; Banerjee, Ayan; Gupta, Sandeep.

2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

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

Sadeghi, K, Sohankar, J, Banerjee, A & Gupta, S 2018, A novel spoofing attack against electroencephalogram-based security systems. in 2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017, San Francisco, United States, 4/4/17. https://doi.org/10.1109/UIC-ATC.2017.8397607
Sadeghi K, Sohankar J, Banerjee A, Gupta S. A novel spoofing attack against electroencephalogram-based security systems. In 2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/UIC-ATC.2017.8397607
Sadeghi, Koosha ; Sohankar, Javad ; Banerjee, Ayan ; Gupta, Sandeep. / A novel spoofing attack against electroencephalogram-based security systems. 2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{047067edfdaa46d8851bb62018c9eda1,
title = "A novel spoofing attack against electroencephalogram-based security systems",
abstract = "Security systems using brain signals or Electroencephalogram (EEG), attempt to exploit chaotic nature of brain signals and their individuality to derive security primitives that are hard to reproduce. In this sense, the signal features are extracted to train a Machine Learning (ML) algorithm for classification. However, although brain signals are chaotic, feature extraction process might reduce the chaos rendering features in a way that they can be generated. Besides, even if features are chaotic, ML techniques might classify them in such a manner that an element in a particular class becomes easy to generate. In this paper, we perform entropy analysis on common features used in EEG-based security systems to estimate their information content, which is used to propose a novel technique for EEG signal generation in feature domain instead of time domain. These generated signals can potentially be used for spoofing attacks. We consider five types of feature extraction techniques and six classifiers found in recently proposed security systems, and analyze their vulnerability to spoofing attacks using generated EEG signals. The results show that the generation scheme can synthesize artificial signals to get classified as genuine brain signals by ML algorithms.",
keywords = "electroencephalogram, entropy, spoofing attack",
author = "Koosha Sadeghi and Javad Sohankar and Ayan Banerjee and Sandeep Gupta",
year = "2018",
month = "6",
day = "26",
doi = "10.1109/UIC-ATC.2017.8397607",
language = "English (US)",
pages = "1--6",
booktitle = "2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A novel spoofing attack against electroencephalogram-based security systems

AU - Sadeghi, Koosha

AU - Sohankar, Javad

AU - Banerjee, Ayan

AU - Gupta, Sandeep

PY - 2018/6/26

Y1 - 2018/6/26

N2 - Security systems using brain signals or Electroencephalogram (EEG), attempt to exploit chaotic nature of brain signals and their individuality to derive security primitives that are hard to reproduce. In this sense, the signal features are extracted to train a Machine Learning (ML) algorithm for classification. However, although brain signals are chaotic, feature extraction process might reduce the chaos rendering features in a way that they can be generated. Besides, even if features are chaotic, ML techniques might classify them in such a manner that an element in a particular class becomes easy to generate. In this paper, we perform entropy analysis on common features used in EEG-based security systems to estimate their information content, which is used to propose a novel technique for EEG signal generation in feature domain instead of time domain. These generated signals can potentially be used for spoofing attacks. We consider five types of feature extraction techniques and six classifiers found in recently proposed security systems, and analyze their vulnerability to spoofing attacks using generated EEG signals. The results show that the generation scheme can synthesize artificial signals to get classified as genuine brain signals by ML algorithms.

AB - Security systems using brain signals or Electroencephalogram (EEG), attempt to exploit chaotic nature of brain signals and their individuality to derive security primitives that are hard to reproduce. In this sense, the signal features are extracted to train a Machine Learning (ML) algorithm for classification. However, although brain signals are chaotic, feature extraction process might reduce the chaos rendering features in a way that they can be generated. Besides, even if features are chaotic, ML techniques might classify them in such a manner that an element in a particular class becomes easy to generate. In this paper, we perform entropy analysis on common features used in EEG-based security systems to estimate their information content, which is used to propose a novel technique for EEG signal generation in feature domain instead of time domain. These generated signals can potentially be used for spoofing attacks. We consider five types of feature extraction techniques and six classifiers found in recently proposed security systems, and analyze their vulnerability to spoofing attacks using generated EEG signals. The results show that the generation scheme can synthesize artificial signals to get classified as genuine brain signals by ML algorithms.

KW - electroencephalogram

KW - entropy

KW - spoofing attack

UR - http://www.scopus.com/inward/record.url?scp=85050195473&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050195473&partnerID=8YFLogxK

U2 - 10.1109/UIC-ATC.2017.8397607

DO - 10.1109/UIC-ATC.2017.8397607

M3 - Conference contribution

SP - 1

EP - 6

BT - 2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -