A closer look tells more: A facial distortion based liveness detection for face authentication

Yan Li; Zilong Wang; Yingjiu Li; Robert Deng; Binbin Chen; Weizhi Meng; Hui Li

doi:10.1145/3321705.3329850

A closer look tells more: A facial distortion based liveness detection for face authentication

Yan Li, Zilong Wang, Yingjiu Li, Robert Deng, Binbin Chen, Weizhi Meng, Hui Li

Department of Applied Mathematics and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Face authentication is vulnerable to media-based virtual face forgery (MVFF) where adversaries display photos/videos or 3D virtual face models of victims to spoof face authentication systems. In this paper, we propose a liveness detection mechanism, called FaceCloseup, to protect the face authentication on mobile devices. FaceCloseup detects MVFF-based attacks by analyzing the distortion of face regions in a user's closeup facial videos captured by built-in camera on mobile device. It can detect MVFF-based attacks with an accuracy of 99.48%.

Original language	English
Title of host publication	Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security
Publisher	Association for Computing Machinery
Publication date	2 Jul 2019
Pages	241-246
ISBN (Electronic)	9781450367523
DOIs	https://doi.org/10.1145/3321705.3329850
Publication status	Published - 2 Jul 2019
Event	2019 ACM Asia Conference on Computer and Communications Security - Auckland, New Zealand Duration: 9 Jul 2019 → 12 Jul 2019

Conference

Conference	2019 ACM Asia Conference on Computer and Communications Security
Country/Territory	New Zealand
City	Auckland
Period	09/07/2019 → 12/07/2019
Sponsor	Association for Computing Machinery

Keywords

Face authentication
Liveness detection
Perspective distortion

Access to Document

10.1145/3321705.3329850

OpenUrl availability

Full text

Cite this

@inproceedings{c721ec77634c4cfe922cb0a5c7e3603f,

title = "A closer look tells more: A facial distortion based liveness detection for face authentication",

abstract = "Face authentication is vulnerable to media-based virtual face forgery (MVFF) where adversaries display photos/videos or 3D virtual face models of victims to spoof face authentication systems. In this paper, we propose a liveness detection mechanism, called FaceCloseup, to protect the face authentication on mobile devices. FaceCloseup detects MVFF-based attacks by analyzing the distortion of face regions in a user's closeup facial videos captured by built-in camera on mobile device. It can detect MVFF-based attacks with an accuracy of 99.48%.",

keywords = "Face authentication, Liveness detection, Perspective distortion",

author = "Yan Li and Zilong Wang and Yingjiu Li and Robert Deng and Binbin Chen and Weizhi Meng and Hui Li",

year = "2019",

month = jul,

day = "2",

doi = "10.1145/3321705.3329850",

language = "English",

pages = "241--246",

booktitle = "Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security",

publisher = "Association for Computing Machinery",

address = "United States",

note = "2019 ACM Asia Conference on Computer and Communications Security, AsiaCCS 2019 ; Conference date: 09-07-2019 Through 12-07-2019",

}

Li, Y, Wang, Z, Li, Y, Deng, R, Chen, B, Meng, W & Li, H 2019, A closer look tells more: A facial distortion based liveness detection for face authentication. in Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security. Association for Computing Machinery, pp. 241-246, 2019 ACM Asia Conference on Computer and Communications Security, Auckland, New Zealand, 09/07/2019. https://doi.org/10.1145/3321705.3329850

A closer look tells more: A facial distortion based liveness detection for face authentication. / Li, Yan; Wang, Zilong; Li, Yingjiu et al.
Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security. Association for Computing Machinery, 2019. p. 241-246.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - A closer look tells more

T2 - 2019 ACM Asia Conference on Computer and Communications Security

AU - Li, Yan

AU - Wang, Zilong

AU - Li, Yingjiu

AU - Deng, Robert

AU - Chen, Binbin

AU - Meng, Weizhi

AU - Li, Hui

PY - 2019/7/2

Y1 - 2019/7/2

N2 - Face authentication is vulnerable to media-based virtual face forgery (MVFF) where adversaries display photos/videos or 3D virtual face models of victims to spoof face authentication systems. In this paper, we propose a liveness detection mechanism, called FaceCloseup, to protect the face authentication on mobile devices. FaceCloseup detects MVFF-based attacks by analyzing the distortion of face regions in a user's closeup facial videos captured by built-in camera on mobile device. It can detect MVFF-based attacks with an accuracy of 99.48%.

AB - Face authentication is vulnerable to media-based virtual face forgery (MVFF) where adversaries display photos/videos or 3D virtual face models of victims to spoof face authentication systems. In this paper, we propose a liveness detection mechanism, called FaceCloseup, to protect the face authentication on mobile devices. FaceCloseup detects MVFF-based attacks by analyzing the distortion of face regions in a user's closeup facial videos captured by built-in camera on mobile device. It can detect MVFF-based attacks with an accuracy of 99.48%.

KW - Face authentication

KW - Liveness detection

KW - Perspective distortion

U2 - 10.1145/3321705.3329850

DO - 10.1145/3321705.3329850

M3 - Article in proceedings

SP - 241

EP - 246

BT - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security

PB - Association for Computing Machinery

Y2 - 9 July 2019 through 12 July 2019

ER -

A closer look tells more: A facial distortion based liveness detection for face authentication

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this