EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Presentation Attack Detection Classification Accuracy: Novel Approaches Incorporating Facial Expressions, Backdrops, and Data Augmentation

Tayyaba Riaz iD, Adeel Anjum iD, Madiha Haider Syed iD, Semeen Rehman iD

Sensors · 28.03.2025 · 25 (7) · 2166

DOI: 10.3390/s25072166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.03.2025. Verfasst von Tayyaba Riaz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Technology, Quaid-e-Azam University Islamabad, Islamabad 45320, Pakistan. Hauptthemen laut MEDLINE: Facial Expression, Biometric Identification, Computer Security, Automated Facial Recognition. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Access Funding by TU Wien.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the evolving landscape of biometric authentication, the integrity of face recognition systems against sophisticated presentation attacks (PAD) is paramount. This study set out to elevate the detection capabilities of PAD systems by ingeniously integrating a teacher–student learning framework with cutting-edge PAD methodologies. Our approach is anchored in the realization that conventional PAD models, while effective to a degree, falter in the face of novel, unseen attack vectors and complex variations. As a solution, we suggest a novel architecture where a teacher network, trained on a comprehensive dataset embodying a broad spectrum of attacks and genuine instances, distills knowledge to a student network. The student network, specifically focusing on the nuanced detection of genuine samples in target domains, leverages minimalist yet representative attack data. This methodology is enriched by incorporating facial expressions, dynamic backgrounds, and adversarially generated attack simulations, aiming to mimic the sophisticated techniques attackers might employ. Through rigorous experimentation and validation on benchmark datasets, our results manifested a substantial leap in classification accuracy, particularly for those samples that have traditionally posed a challenge. The newly proposed model, which can not only effectively outperform existing PAD solutions, but also achieve admirable flexibility and applicability to novel attack scenarios, truly demonstrates the power of the proposed teacher–student framework. This paves the way for improved security and trustworthiness in the area of face recognition systems and the deployment of biometric technologies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Facial ExpressionBiometric IdentificationComputer SecurityAutomated Facial RecognitionHumansAlgorithmsFace

Stichwörter der Autor:innen

adversarial trainingdata augmentationdecision-making accuracyface presentation attack detectionknowledge distillationone-class domain adaptationsparse learning

Autor:innen und Institutionen

  • Institute of Information Technology, Quaid-e-Azam University Islamabad, Islamabad 45320, Pakistan.
  • Institute of Computer Technology, Technical University of Vienna (TU Wien), 1040 Vienna, Austria.

ORCID-Profile: Tayyaba Riaz, Adeel Anjum, Madiha Haider Syed, Semeen Rehman

Förderung

  • Open Access Funding by TU Wien

Zitieren

APA

Riaz, T., Anjum, A., Syed, M. H., & Rehman, S. (2025). Improving Presentation Attack Detection Classification Accuracy: Novel Approaches Incorporating Facial Expressions, Backdrops, and Data Augmentation. Sensors, 25(7), 2166. https://doi.org/10.3390/s25072166

Vancouver

Riaz T, Anjum A, Syed MH, Rehman S. Improving Presentation Attack Detection Classification Accuracy: Novel Approaches Incorporating Facial Expressions, Backdrops, and Data Augmentation. Sensors. 2025;25(7):2166. doi:10.3390/s25072166

BibTeX
@article{Riaz2025,
  author = {Riaz, Tayyaba and Anjum, Adeel and Syed, Madiha Haider and Rehman, Semeen},
  title = {Improving Presentation Attack Detection Classification Accuracy: Novel Approaches Incorporating Facial Expressions, Backdrops, and Data Augmentation},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {7},
  pages = {2166},
  doi = {10.3390/s25072166}
}
Kostenlos starten →