Metraipolis › archive › dc_088cfd962125

Grounding-Aware Judge Reward Reinforcement Learning for Out-of-Domain Face Anti-Spoofing — arXiv:2611.09047

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09047
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:13.043Z
SHA-256 of the archived text
d835cf65b07c515a364bf0187b16cc3c653eb137219a10299b85700aedf2bfc7
Stable URL of this page
https://metraipolis.com/documento/dc_088cfd962125

How to cite

Grounding-Aware Judge Reward Reinforcement Learning for Out-of-Domain Face Anti-Spoofing — arXiv:2611.09047 — arXiv (en), https://arxiv.org/abs/2611.09047 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_088cfd962125 (Metraipolis archive dc_088cfd962125, sha256 d835cf65b07c515a364bf0187b16cc3c653eb137219a10299b85700aedf2bfc7)
BibTeX
@misc{dc088cfd962125,
  title = {Grounding-Aware Judge Reward Reinforcement Learning for Out-of-Domain Face Anti-Spoofing — arXiv:2611.09047},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09047},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_088cfd962125; sha256 d835cf65b07c515a364bf0187b16cc3c653eb137219a10299b85700aedf2bfc7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09047. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Face Anti-Spoofing (FAS) must distinguish genuine faces from presentation attacks. A unified Multimodal Large Language Model (MLLM) is an attractive solution: it detects physical attacks (print, replay, mask) in one model and produces interpretable forensic evidence via Chain-of-Thought (CoT). A central obstacle to post-training such a model with reinforcement learning is that FAS reasoning has no rule-verifiable ground truth: only the binary verdict is checkable, while the reasoning chain cannot be verified by any hand-crafted rule. Optimizing the verdict alone is therefore a sparse, hackable signal. The model can reach the correct answer through a shortcut such as a false-rejection bias, which does not generalize. We address this with a grounding-aware judge reward. A 32B vision-language judge scores each reasoning chain against the image on evidence anchoring, logical coherence, and domain knowledge, turning the image itself into the verification signal. The reward is applied in a Group Relative Policy Optimization (GRPO) stage after CoT supervised fine-tuning. It is the judge, rather than the RL objective, that supplies the process supervision a verdict-only reward cannot. Our study starts from a model that already performs well In-Domain (ID) after CoT-based supervised fine-tuning and asks how to improve its Out-of-Domain (OOD) generalization. We find that grounding-aware rewards are an effective means to that end. We validate the method on OOD generalization, where the reward reduces ACER on two physical benchmarks (LCC-FASD 0.288 to 0.273, MSU-MFSD 0.431 to 0.409) while preserving ID accuracy (CelebA-Spoof 0.033 to 0.035). Against ResNet-50/101 and CLIP-ViT-B/16 baselines, the MLLM dominates ID and matches or surpasses the strongest baseline OOD. To our knowledge this is the first use of LLM-as-judge process supervision for FAS.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.09047 — 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 2026-11-09T22:37:47.218Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).