UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914547525222400 |
|---|---|
| author | Li, Hongrui Shi, Yichen Wang, Hongyang Gao, Yuhao Ma, Hui Feng, Jun Yu, Zitong |
| author_facet | Li, Hongrui Shi, Yichen Wang, Hongyang Gao, Yuhao Ma, Hui Feng, Jun Yu, Zitong |
| contents | Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminative or prompt-based methods largely rely on appearance correlations and provide limited evidence-grounded reasoning. We propose UniShield, a knowledge-grounded multimodal reasoning framework for unified face attack defense. UniShield constructs a Face Attack Knowledge Graph (FAKG) that links attack categories to diagnostic visual cues and attack-conditioned relations, and uses it to synthesize 52,025 FAKG-QA examples for Attack-Graph Instruction Tuning (AGIT). To improve rationale consistency, we further introduce Graph-Consistent Reasoning Optimization (GCRO), a GRPO-based objective with a KG-consistency reward that encourages generated rationales to match graph-supported cues while penalizing incompatible claims. Experiments on our multimodal UAD benchmark show that UniShield achieves strong performance across binary, coarse-grained, and fine-grained protocols, with consistently high ACC and low HTER. These results suggest that structured attack knowledge can improve both detection accuracy and reasoning reliability over discriminative baselines and general-purpose MLLMs. Our code will be released at https://anonymous.4open.science/r/Unishield-A6A3/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08709 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning Li, Hongrui Shi, Yichen Wang, Hongyang Gao, Yuhao Ma, Hui Feng, Jun Yu, Zitong Computer Vision and Pattern Recognition Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminative or prompt-based methods largely rely on appearance correlations and provide limited evidence-grounded reasoning. We propose UniShield, a knowledge-grounded multimodal reasoning framework for unified face attack defense. UniShield constructs a Face Attack Knowledge Graph (FAKG) that links attack categories to diagnostic visual cues and attack-conditioned relations, and uses it to synthesize 52,025 FAKG-QA examples for Attack-Graph Instruction Tuning (AGIT). To improve rationale consistency, we further introduce Graph-Consistent Reasoning Optimization (GCRO), a GRPO-based objective with a KG-consistency reward that encourages generated rationales to match graph-supported cues while penalizing incompatible claims. Experiments on our multimodal UAD benchmark show that UniShield achieves strong performance across binary, coarse-grained, and fine-grained protocols, with consistently high ACC and low HTER. These results suggest that structured attack knowledge can improve both detection accuracy and reasoning reliability over discriminative baselines and general-purpose MLLMs. Our code will be released at https://anonymous.4open.science/r/Unishield-A6A3/. |
| title | UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.08709 |