# SpatialTrust: A Benchmark for Environmental Risk Recognition in Secure Authentication

arXiv: https://arxiv.org/abs/2608.29489 · HTML: https://mlsanity.com/paper/2608.29489/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [Visual7W: Grounded Question Answering in Images](https://mlsanity.com/paper/1511.03416/) (2015)
- [MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models](https://mlsanity.com/paper/2311.17600/) (2023)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models](https://mlsanity.com/paper/2511.16940/) (2025)
- [Towards Baselines for Shoulder Surfing on Mobile Authentication](https://mlsanity.com/paper/1709.04959/) (2017)
- [Examining the Examiners: Students' Privacy and Security Perceptions of Online Proctoring Services](https://mlsanity.com/paper/2106.05917/) (2021)
- [Balancing The Perception of Cheating Detection, Privacy and Fairness: A Mixed-Methods Study of Visual Data Obfuscation in Remote Proctoring](https://mlsanity.com/paper/2406.15074/) (2024)

## Abstract (arXiv)

Visual environmental risk recognition plays an important role in secure authentication, where a user's surroundings may reveal sensitive information or introduce potential security risks. However, existing evaluations of multimodal large language models (MLLMs) rarely examine whether models can reliably recognize, localize, and explain such risks in spatially grounded authentication scenarios. We present SpatialTrust, a question-answering benchmark for evaluating environmental risk recognition in secure authentication. SpatialTrust assesses five complementary abilities: sensitive factor detection, direct factor identification, indirect factor identification, direct factor explanation, and indirect factor explanation. We evaluate both proprietary and open-source MLLMs and find that current models show limited performance, especially in understanding and explaining indirect risks, indicating that spatial risk awareness remains a challenging capability for MLLMs. In addition, we introduce SpatialTrustGuard, a structured QA-and-audit pipeline that improves Qwen3-VL-30B-A3B-Instruct from 36.78% to 41.12% overall. Our findings highlight the need for dedicated benchmarks and structured inference methods to improve the trustworthiness of MLLMs in secure authentication.