Hide my Gaze with EOG! Towards Closed-Eye Gaze Gesture Passwords that Resist Observation-Attacks with Electrooculography in Smart Glasses

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Hide my Gaze with EOG! Towards Closed-Eye Gaze Gesture Passwords that Resist Observation-Attacks with Electrooculography in Smart Glasses. / Findling, Rainhard; Quddus, Tahmid; Sigg, Stephan.

17th International Conference on Advances in Mobile Computing & Multimedia (MoMM2019). ACM, 2019.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Findling, R, Quddus, T & Sigg, S 2019, Hide my Gaze with EOG! Towards Closed-Eye Gaze Gesture Passwords that Resist Observation-Attacks with Electrooculography in Smart Glasses. in 17th International Conference on Advances in Mobile Computing & Multimedia (MoMM2019). ACM, International Conference on Advances in Mobile Computing and Multimedia, Munich, Germany, 02/12/2019. https://doi.org/10.1145/3365921.3365922

APA

Findling, R., Quddus, T., & Sigg, S. (Accepted/In press). Hide my Gaze with EOG! Towards Closed-Eye Gaze Gesture Passwords that Resist Observation-Attacks with Electrooculography in Smart Glasses. In 17th International Conference on Advances in Mobile Computing & Multimedia (MoMM2019) ACM. https://doi.org/10.1145/3365921.3365922

Vancouver

Findling R, Quddus T, Sigg S. Hide my Gaze with EOG! Towards Closed-Eye Gaze Gesture Passwords that Resist Observation-Attacks with Electrooculography in Smart Glasses. In 17th International Conference on Advances in Mobile Computing & Multimedia (MoMM2019). ACM. 2019 https://doi.org/10.1145/3365921.3365922

Author

Findling, Rainhard ; Quddus, Tahmid ; Sigg, Stephan. / Hide my Gaze with EOG! Towards Closed-Eye Gaze Gesture Passwords that Resist Observation-Attacks with Electrooculography in Smart Glasses. 17th International Conference on Advances in Mobile Computing & Multimedia (MoMM2019). ACM, 2019.

Bibtex - Download

@inproceedings{260fdd84cf944ba8a681d2f1a4296ee8,
title = "Hide my Gaze with EOG!: Towards Closed-Eye Gaze Gesture Passwords that Resist Observation-Attacks with Electrooculography in Smart Glasses",
abstract = "Smart glasses allow for gaze gesture passwords as a hands-free form of mobile authentication. However, pupil movements for password input are easily observed by attackers, who thereby can derive the password. In this paper we investigate closed-eye gaze gesture passwords with EOG sensors in smart glasses. We propose an approach to detect and recognize closed-eye gaze gestures, together with a 7 and 9 character gaze gesture alphabet. Our evaluation indicates good gaze gesture detection rates. However, recognition is challenging specifically for vertical eye movements with 71.2{\%}-86.5{\%} accuracy and better results for opened than closed eyes. We further find that closed-eye gaze gesture passwords are difficult to attack from observations with 0{\%} success rate in our evaluation, while attacks on open eye passwords succeed with 61{\%}. This indicates that closed-eye gaze gesture passwords protect the authentication secret significantly better than their open eye counterparts.",
keywords = "authentication, closed-eye, EOG sensors, hands-free, gaze gestures, mobile, password, smart glasses",
author = "Rainhard Findling and Tahmid Quddus and Stephan Sigg",
note = "Avaa k{\"a}sikirjoitus, kun konf. julkaistu.",
year = "2019",
doi = "10.1145/3365921.3365922",
language = "English",
booktitle = "17th International Conference on Advances in Mobile Computing & Multimedia (MoMM2019)",
publisher = "ACM",

}

RIS - Download

TY - GEN

T1 - Hide my Gaze with EOG!

T2 - Towards Closed-Eye Gaze Gesture Passwords that Resist Observation-Attacks with Electrooculography in Smart Glasses

AU - Findling, Rainhard

AU - Quddus, Tahmid

AU - Sigg, Stephan

N1 - Avaa käsikirjoitus, kun konf. julkaistu.

PY - 2019

Y1 - 2019

N2 - Smart glasses allow for gaze gesture passwords as a hands-free form of mobile authentication. However, pupil movements for password input are easily observed by attackers, who thereby can derive the password. In this paper we investigate closed-eye gaze gesture passwords with EOG sensors in smart glasses. We propose an approach to detect and recognize closed-eye gaze gestures, together with a 7 and 9 character gaze gesture alphabet. Our evaluation indicates good gaze gesture detection rates. However, recognition is challenging specifically for vertical eye movements with 71.2%-86.5% accuracy and better results for opened than closed eyes. We further find that closed-eye gaze gesture passwords are difficult to attack from observations with 0% success rate in our evaluation, while attacks on open eye passwords succeed with 61%. This indicates that closed-eye gaze gesture passwords protect the authentication secret significantly better than their open eye counterparts.

AB - Smart glasses allow for gaze gesture passwords as a hands-free form of mobile authentication. However, pupil movements for password input are easily observed by attackers, who thereby can derive the password. In this paper we investigate closed-eye gaze gesture passwords with EOG sensors in smart glasses. We propose an approach to detect and recognize closed-eye gaze gestures, together with a 7 and 9 character gaze gesture alphabet. Our evaluation indicates good gaze gesture detection rates. However, recognition is challenging specifically for vertical eye movements with 71.2%-86.5% accuracy and better results for opened than closed eyes. We further find that closed-eye gaze gesture passwords are difficult to attack from observations with 0% success rate in our evaluation, while attacks on open eye passwords succeed with 61%. This indicates that closed-eye gaze gesture passwords protect the authentication secret significantly better than their open eye counterparts.

KW - authentication

KW - closed-eye

KW - EOG sensors

KW - hands-free

KW - gaze gestures

KW - mobile

KW - password

KW - smart glasses

U2 - 10.1145/3365921.3365922

DO - 10.1145/3365921.3365922

M3 - Conference contribution

BT - 17th International Conference on Advances in Mobile Computing & Multimedia (MoMM2019)

PB - ACM

ER -

ID: 37133254