TU Darmstadt / ULB / TUbiblio

On the Generalization of Detecting Face Morphing Attacks as Anomalies: Novelty vs. Outlier Detection

Damer, Naser and Grebe, Jonas Henry and Zienert, Steffen and Kirchbuchner, Florian and Kuijper, Arjan (2019):
On the Generalization of Detecting Face Morphing Attacks as Anomalies: Novelty vs. Outlier Detection.
pp. 1-5, IEEE, 10th International Conference on Biometrics Theory, Applications and Systems (BTAS 2019), Tampa, USA, 23.-26.09., ISBN 978-1-7281-1523-8,
DOI: 10.1109/BTAS46853.2019.9185995,
[Conference or Workshop Item]

Abstract

Face morphing attacks are verifiable to multiple identities, leading to faulty identity links. Recent works have studied the face morphing attack detection performance over variations in morphing approaches, pointing out low generalization. This work studies detecting these attacks as anomalies and discusses the performance and generalization over different morphing types. We also analyze the accuracy and generalization effect of including different amounts of attack contamination in the anomaly training data (novelty vs. outlier). This is performed with two baseline 2-class classifiers, two approaches for anomaly detection, two image feature extractions, two morphing types, and variations in contamination levels and tolerated training errors. The results points out the relative lower performance, but higher generalization ability, of anomaly detection in comparison to 2-class classifiers, along with the benefits of contaminating the anomaly training data.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Damer, Naser and Grebe, Jonas Henry and Zienert, Steffen and Kirchbuchner, Florian and Kuijper, Arjan
Title: On the Generalization of Detecting Face Morphing Attacks as Anomalies: Novelty vs. Outlier Detection
Language: English
Abstract:

Face morphing attacks are verifiable to multiple identities, leading to faulty identity links. Recent works have studied the face morphing attack detection performance over variations in morphing approaches, pointing out low generalization. This work studies detecting these attacks as anomalies and discusses the performance and generalization over different morphing types. We also analyze the accuracy and generalization effect of including different amounts of attack contamination in the anomaly training data (novelty vs. outlier). This is performed with two baseline 2-class classifiers, two approaches for anomaly detection, two image feature extractions, two morphing types, and variations in contamination levels and tolerated training errors. The results points out the relative lower performance, but higher generalization ability, of anomaly detection in comparison to 2-class classifiers, along with the benefits of contaminating the anomaly training data.

Publisher: IEEE
ISBN: 978-1-7281-1523-8
Uncontrolled Keywords: Biometrics, Machine learning, Face recognition, Spoofing attacks
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: 10th International Conference on Biometrics Theory, Applications and Systems (BTAS 2019)
Event Location: Tampa, USA
Event Dates: 23.-26.09.
Date Deposited: 22 Sep 2020 13:28
DOI: 10.1109/BTAS46853.2019.9185995
Official URL: https://doi.org/10.1109/BTAS46853.2019.9185995
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details