The results indicate that a properly structured vision-only architecture can achieve state-of-the-art performance in unified FAS without the need for multimodal supervision.
Abstract
With the increasing diversity of spoofing attacks, there is a growing demand for unified Face Anti-Spoofing (FAS) models capable of detecting both physical and digital threats. While existing Vision-Language Models (VLMs) demonstrate high generalization in this context, they heavily rely on complex multimodal fusion and external text encoders. In this paper, we propose DINO-VPT, a lightweight, vision-only framework leveraging hierarchical visual prompt tuning. By dynamically injecting prompts conditioned on input features via a Prompt Routing Network (PRN), our method effectively disentangles diverse spoofing artifacts without requiring multimodal fusion. Evaluations on the UniAttackData benchmark demonstrate that DINO-VPT achieves higher accuracy than state-of-the-art VLM-based methods. Our results indicate that a properly structured vision-only architecture can achieve state-of-the-art performance in unified FAS without the need for multimodal supervision.
A few-shot, high-quality semantic annotation paradigm is effective for building trustworthy, explainable, and cost-efficient UFAD systems, and validating the robustness of semantic anchoring compared to models trained on massive short-text data.
Xiao-Yong Yu, Rong-Zhen Li, Shu-Ming Shi et al.· 0 citations
Face Anti-Spoofing (FAS) is a crucial task for securing face recognition systems, yet its cross-domain generalization remains challenging. Recently, vision-language methods built upon pretrained models such as CLIP have shown promising performance in addressing these cross-domain scenarios. Nevertheless, existing appro...
Xiao-Meng Wei, Wen-Zhong Yang, Ya-Bo Yin et al.· Journal of King Saud Univers...· 0 citations
This research provides a resilient forensic layer for digital identity verification, ensuring evidence integrity in the GenAI era by proposing a novel Multimodal Deep Learning framework designed to detect high-fidelity Deepfakes by exploiting audio visual temporal inconsistencies.
H. Truong, D. T. Luong, Tuan Tran· Journal of Science and Techn...· 0 citations
A novel E-Branchformer-based architecture that effectively leverages self-supervised speech representations for audio deepfake detection and employs parallel branches to simultaneously capture global contextual dependencies through multi-head self-attention and local temporal patterns through convolutional processing.
Phuong Dat, Học Thủ, T. Nguyễn et al.· 0 citations
As image generation and editing technologies have progressed substantially, facial forgeries pose significant challenges to privacy and public safety. Due to limited ability to capture forgery cues, existing small-scale forgery detection models often struggle to generalize across various domains and unseen manipulation...
Feng-Ming Gu, Ming-Jie He, Zong-Hui Guo et al.· 0 citations
This work proposes a compositional forensic visual prompt learning framework that operates entirely in the visual feature space and employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units derived from image patches.
Fangling Jiang, Qi Li, Bing Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
