# SLAPBench: Benchmarking Multimodal Large Language Models for Four-Finger SLAP Fingerprint Verification

arXiv: https://arxiv.org/abs/2607.15517 · HTML: https://mlsanity.com/paper/2607.15517/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 9 of 9)

- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models](https://mlsanity.com/paper/2407.11691/) (2024)
- [Learning a Fixed-Length Fingerprint Representation](https://mlsanity.com/paper/1909.09901/) (2019)
- [FingerNet: An Unified Deep Network for Fingerprint Minutiae Extraction](https://mlsanity.com/paper/1709.02228/) (2017)
- [FaceXBench: Evaluating Multimodal LLMs on Face Understanding](https://mlsanity.com/paper/2501.10360/) (2025)
- [Benchmarking Multimodal Large Language Models for Face Recognition](https://mlsanity.com/paper/2510.14866/) (2025)
- [Deep Age-Invariant Fingerprint Segmentation System](https://mlsanity.com/paper/2303.03341/) (2023)
- [Evaluating Multimodal Large Language Models for Heterogeneous Face Recognition](https://mlsanity.com/paper/2601.15406/) (2026)
- [FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint Analysis](https://mlsanity.com/paper/2512.18073/) (2025)

## Abstract (arXiv)

Four-finger SLAP fingerprints are flat live-scan impressions of the index, middle, ring, and little fingers of one hand, used for identity verification in border control and law enforcement. No benchmark has evaluated whether multimodal large language models (MLLMs) can verify identity from SLAP images. We introduce SLAPBench, the first benchmark for MLLM-based four-finger SLAP fingerprint verification, built from NIST SD302b with 7,832 pairs (176 mated, 7,656 non-mated). We evaluate four open-source MLLMs (InternVL3-8B, Qwen2.5-VL-7B, Qwen3-VL-8B, Gemma-3-12B) and the proprietary Claude Opus 4.8 under zero-shot, task-description, and similarity-scoring prompts. Prompting governs verification behavior. Task-description prompting collapses all four open-source models to near-100% False Accept Rate (FAR), and Gemma-3-12B collapses under zero-shot as well; Claude Opus 4.8 alone resists collapse under both binary prompts, giving the best binary result (FAR = 20.2%). Similarity scoring removes collapse across the open-source models and exposes wide capability gaps: Claude reaches AUC = 0.953 and Gemma-3-12B 0.837, while InternVL3-8B is inverted (AUC = 0.590) and Qwen2.5-VL-7B near random (0.567). Qwen3-VL-8B attains perfect separation (AUC = 1.000), which we treat as a diagnostic rather than as capability: SD302b holds one SLAP capture per finger position, so mated pairs are cross-resolution. A matched-resolution control leaves the perfect score intact, ruling out the resolution shortcut; what cannot be excluded within SD302b is near-duplicate detection, since a mated pair is one capture rendered twice. A fairness probe over gender, race, and age suggests disparity grows as discrimination weakens. SLAPBench establishes the first SLAP-specific MLLM baseline and shows that prompting governs collapse while model capability governs discrimination.