Poster: Secure authentication from facial attributes with no privacy loss

Orr Dunkelman; Margarita Osadchy; Mahmood Sharif

doi:10.1145/2508859.2512511

Poster: Secure authentication from facial attributes with no privacy loss

Orr Dunkelman, Margarita Osadchy, Mahmood Sharif

Department of Computer Science

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

Abstract

Biometric authentication is more secure than using regular passwords, as biometrics cannot be "forgotten" and contain high entropy. Thus, many constructions rely on biometric features for authentication, and use them as a source for "good" cryptographic keys. At the same time, biometric systems carry with them many privacy concerns. We describe a proof-of-concept (PoC) which transforms facial attributes from a single image into keys in a consistent, discriminative, and privacy-aware manner. The outcome is a user-specific string that cannot be guessed, and it reveals no information concerning the users of the system, even when the system's secrets are revealed.

Original language	English
Title of host publication	CCS 2013 - Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security
Pages	1403-1405
Number of pages	3
DOIs	https://doi.org/10.1145/2508859.2512511
State	Published - 2013
Event	2013 ACM SIGSAC Conference on Computer and Communications Security, CCS 2013 - Berlin, Germany Duration: 4 Nov 2013 → 8 Nov 2013

Publication series

Name	Proceedings of the ACM Conference on Computer and Communications Security
ISSN (Print)	1543-7221

Conference

Conference	2013 ACM SIGSAC Conference on Computer and Communications Security, CCS 2013
Country/Territory	Germany
City	Berlin
Period	4/11/13 → 8/11/13

Keywords

biometric credentials
face recognition
privacy-preserving

ASJC Scopus subject areas

Software
Computer Networks and Communications

Access to Document

10.1145/2508859.2512511

Cite this

@inproceedings{dafe279d16f0454eae9122c53cd7d96e,

title = "Poster: Secure authentication from facial attributes with no privacy loss",

abstract = "Biometric authentication is more secure than using regular passwords, as biometrics cannot be {"}forgotten{"} and contain high entropy. Thus, many constructions rely on biometric features for authentication, and use them as a source for {"}good{"} cryptographic keys. At the same time, biometric systems carry with them many privacy concerns. We describe a proof-of-concept (PoC) which transforms facial attributes from a single image into keys in a consistent, discriminative, and privacy-aware manner. The outcome is a user-specific string that cannot be guessed, and it reveals no information concerning the users of the system, even when the system's secrets are revealed.",

keywords = "biometric credentials, face recognition, privacy-preserving",

author = "Orr Dunkelman and Margarita Osadchy and Mahmood Sharif",

year = "2013",

doi = "10.1145/2508859.2512511",

language = "English",

isbn = "9781450324779",

series = "Proceedings of the ACM Conference on Computer and Communications Security",

pages = "1403--1405",

booktitle = "CCS 2013 - Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security",

note = "2013 ACM SIGSAC Conference on Computer and Communications Security, CCS 2013 ; Conference date: 04-11-2013 Through 08-11-2013",

}

Dunkelman, O , Osadchy, M & Sharif, M 2013, Poster: Secure authentication from facial attributes with no privacy loss. in CCS 2013 - Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security. Proceedings of the ACM Conference on Computer and Communications Security, pp. 1403-1405, 2013 ACM SIGSAC Conference on Computer and Communications Security, CCS 2013, Berlin, Germany, 4/11/13. https://doi.org/10.1145/2508859.2512511

Poster: Secure authentication from facial attributes with no privacy loss. / Dunkelman, Orr ; Osadchy, Margarita; Sharif, Mahmood.
CCS 2013 - Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security. 2013. p. 1403-1405 (Proceedings of the ACM Conference on Computer and Communications Security).

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

TY - GEN

T1 - Poster

T2 - 2013 ACM SIGSAC Conference on Computer and Communications Security, CCS 2013

AU - Dunkelman, Orr

AU - Osadchy, Margarita

AU - Sharif, Mahmood

PY - 2013

Y1 - 2013

N2 - Biometric authentication is more secure than using regular passwords, as biometrics cannot be "forgotten" and contain high entropy. Thus, many constructions rely on biometric features for authentication, and use them as a source for "good" cryptographic keys. At the same time, biometric systems carry with them many privacy concerns. We describe a proof-of-concept (PoC) which transforms facial attributes from a single image into keys in a consistent, discriminative, and privacy-aware manner. The outcome is a user-specific string that cannot be guessed, and it reveals no information concerning the users of the system, even when the system's secrets are revealed.

AB - Biometric authentication is more secure than using regular passwords, as biometrics cannot be "forgotten" and contain high entropy. Thus, many constructions rely on biometric features for authentication, and use them as a source for "good" cryptographic keys. At the same time, biometric systems carry with them many privacy concerns. We describe a proof-of-concept (PoC) which transforms facial attributes from a single image into keys in a consistent, discriminative, and privacy-aware manner. The outcome is a user-specific string that cannot be guessed, and it reveals no information concerning the users of the system, even when the system's secrets are revealed.

KW - biometric credentials

KW - face recognition

KW - privacy-preserving

UR - http://www.scopus.com/inward/record.url?scp=84889073773&partnerID=8YFLogxK

U2 - 10.1145/2508859.2512511

DO - 10.1145/2508859.2512511

M3 - Conference contribution

AN - SCOPUS:84889073773

SN - 9781450324779

T3 - Proceedings of the ACM Conference on Computer and Communications Security

SP - 1403

EP - 1405

BT - CCS 2013 - Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security

Y2 - 4 November 2013 through 8 November 2013

ER -

Poster: Secure authentication from facial attributes with no privacy loss

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this