Metraipolis › archive › dc_dc826e29d396
Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection — arXiv:2608.29802
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29802
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:07.508Z
- SHA-256 of the archived text
1f6a53777633781c7f271932cd479f5640d1e0c6d11c96af3dbfc483d832d13f- Stable URL of this page
https://metraipolis.com/documento/dc_dc826e29d396
How to cite
Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection — arXiv:2608.29802 — arXiv (en), https://arxiv.org/abs/2608.29802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc826e29d396 (Metraipolis archive dc_dc826e29d396, sha256 1f6a53777633781c7f271932cd479f5640d1e0c6d11c96af3dbfc483d832d13f)
BibTeX
@misc{dcdc826e29d396,
title = {Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection — arXiv:2608.29802},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29802},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc826e29d396; sha256 1f6a53777633781c7f271932cd479f5640d1e0c6d11c96af3dbfc483d832d13f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Face recognition systems are increasingly deployed in security-critical applications, yet they remain vulnerable to presentation and morph attacks. Presentation attack detection (PAD) and morphing attack detection (MAD) are therefore essential components of trustworthy face biometrics. Despite advancements in PAD and MAD methods, existing detectors suffer from limited generalization and degrade in cross-dataset evaluation. In this paper, we systematically investigate whether general-purpose foundation models (FMs) and multimodal large language models (MLLMs) encode PAD-relevant and MAD-relevant information, and how such models can best be deployed for both tasks. We study five approaches with increasing access to the internal information of the model: (i) zero-shot prompting of off-the-shelf MLLMs; (ii) training a shallow model on the next-token logit probabilities at the output of the MLLM; (iii) parameter-efficient fine-tuning on task-specific question-answer data, yielding two specialized MLLMs, called PADLLM and MADLLM, which additionally provide textual reasoning for their decisions; (iv) linear probing of frozen vision encoders; and (v) fine-tuning of vision encoders of FMs and MLLMs. We benchmark 16 open-weight MLLMs and 30 vision encoder backbones on four PAD datasets (MSU-MFSD, CASIA-FASD, Replay-Attack, and OULU-NPU) and four MAD datasets (FFHQ, FRGC, FRLL, and FERET). Our experiments show that FMs and MLLMs can achieve significant performance for PAD and MAD. In addition, the fine-tuned models achieve state-of-the-art detection performance in cross-dataset evaluation, indicating that general-purpose pretrained representations carry substantial attack-relevant information. Source code of all our experiments will be publicly released. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29802 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:48.068Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).