# BadNAVer: Exploring Jailbreak Attacks On Vision-and-Language Navigation

arXiv: https://arxiv.org/abs/2505.12443 · HTML: https://mlsanity.com/paper/2505.12443/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- First posted on arXiv 18 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Built on by (most cited first, 2 of 2)

- [Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses](https://mlsanity.com/paper/2605.02900/) (2026)
- [Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark](https://mlsanity.com/paper/2510.02356/) (2025)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have recently gained attention for their generalization and reasoning capabilities in Vision-and-Language Navigation (VLN) tasks, leading to the rise of MLLM-driven navigators. However, MLLMs are vulnerable to jailbreak attacks, where crafted prompts bypass safety mechanisms and trigger undesired outputs. In embodied scenarios, such vulnerabilities pose greater risks: unlike plain text models that generate toxic content, embodied agents may interpret malicious instructions as executable commands, potentially leading to real-world harm. In this paper, we present the first systematic jailbreak attack paradigm targeting MLLM-driven navigator. We propose a three-tiered attack framework and construct malicious queries across four intent categories, concatenated with standard navigation instructions. In the Matterport3D simulator, we evaluate navigation agents powered by five MLLMs and report an average attack success rate over 90%. To test real-world feasibility, we replicate the attack on a physical robot. Our results show that even well-crafted prompts can induce harmful actions and intents in MLLMs, posing risks beyond toxic output and potentially leading to physical harm.