BadNAVer: 視覚言語ナビゲーションに対するジェイルブレイク攻撃の探索
BadNAVer: Exploring Jailbreak Attacks On Vision-and-Language Navigation
MLLM駆動の視覚言語ナビゲータに対する初の体系的なジェイルブレイク攻撃を提案し、シミュレータと実機で90%超の攻撃成功率を示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Wenqi Lyu, Zerui Li, Yanyuan Qiao, Qi Wu
分類: cs.RO
原文アブストラクト
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.
