Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Guo, Jiabao, Wang, Yadian, Ma, Hui, Fu, Yuhao, Jia, Ju, Liu, Hui, Tang, Shengeng, Cheng, Lechao, Diao, Yunfeng, Liu, Ajian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914184965390336
author Guo, Jiabao
Wang, Yadian
Ma, Hui
Fu, Yuhao
Jia, Ju
Liu, Hui
Tang, Shengeng
Cheng, Lechao
Diao, Yunfeng
Liu, Ajian
author_facet Guo, Jiabao
Wang, Yadian
Ma, Hui
Fu, Yuhao
Jia, Ju
Liu, Hui
Tang, Shengeng
Cheng, Lechao
Diao, Yunfeng
Liu, Ajian
contents Real-world face recognition systems are vulnerable to both physical presentation attacks (PAs) and digital forgery attacks (DFs). We aim to achieve comprehensive protection of biometric data by implementing a unified physical-digital defense framework with advanced detection. Existing approaches primarily employ CLIP with regularization constraints to enhance model generalization across both tasks. However, these methods suffer from conflicting optimization directions between physical and digital attack detection under same category prompt spaces. To overcome this limitation, we propose a Spoofing-aware Prompt Learning for Unified Attack Detection (SPL-UAD) framework, which decouples optimization branches for physical and digital attacks in the prompt space. Specifically, we construct a learnable parallel prompt branch enhanced with adaptive Spoofing Context Prompt Generation, enabling independent control of optimization for each attack type. Furthermore, we design a Cues-awareness Augmentation that leverages the dual-prompt mechanism to generate challenging sample mining tasks on data, significantly enhancing the model's robustness against unseen attack types. Extensive experiments on the large-scale UniAttackDataPlus dataset demonstrate that the proposed method achieves significant performance improvements in unified attack detection tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06363
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection
Guo, Jiabao
Wang, Yadian
Ma, Hui
Fu, Yuhao
Jia, Ju
Liu, Hui
Tang, Shengeng
Cheng, Lechao
Diao, Yunfeng
Liu, Ajian
Computer Vision and Pattern Recognition
Real-world face recognition systems are vulnerable to both physical presentation attacks (PAs) and digital forgery attacks (DFs). We aim to achieve comprehensive protection of biometric data by implementing a unified physical-digital defense framework with advanced detection. Existing approaches primarily employ CLIP with regularization constraints to enhance model generalization across both tasks. However, these methods suffer from conflicting optimization directions between physical and digital attack detection under same category prompt spaces. To overcome this limitation, we propose a Spoofing-aware Prompt Learning for Unified Attack Detection (SPL-UAD) framework, which decouples optimization branches for physical and digital attacks in the prompt space. Specifically, we construct a learnable parallel prompt branch enhanced with adaptive Spoofing Context Prompt Generation, enabling independent control of optimization for each attack type. Furthermore, we design a Cues-awareness Augmentation that leverages the dual-prompt mechanism to generate challenging sample mining tasks on data, significantly enhancing the model's robustness against unseen attack types. Extensive experiments on the large-scale UniAttackDataPlus dataset demonstrate that the proposed method achieves significant performance improvements in unified attack detection tasks.
title Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.06363