揭示VLN鲁棒性：基于室内光照的对抗攻击黑盒框架
Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack
提出通过操纵室内全局光照（静态强度变化与动态开关切换）对VLN智能体进行黑盒对抗攻击的框架，为视觉导航模型的鲁棒性评估提供了现实可行的扰动范式，可启发针对光照变化的防御与数据增强策略。
原文依据 We propose Indoor Lighting-based Adversarial Attack (ILA), a black-box framework that manipulates global illumination to disrupt VLN agents.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉语言导航（VLN）智能体已取得显著进展，但其鲁棒性仍未得到充分研究。现有的对抗评估往往依赖于在日常室内环境中很少遇到的异常纹理扰动。在这种人为条件下出现的错误实际意义有限，因为真实世界中的智能体不太可能遇到此类人工模式。在本工作中，我们关注室内光照——一种内在但很大程度上被忽视的场景属性，它强烈影响导航。我们提出了基于室内光照的对抗攻击（ILA），这是一个操纵全局光照以破坏VLN智能体的黑盒框架。受典型家庭照明使用习惯的启发，我们设计了两种攻击模式：静态室内光照攻击（SILA），其中光照强度在整个回合中保持不变；以及动态室内光照攻击（DILA），其中灯光在关键时刻打开或关闭以引发突然的光照变化。我们在三个导航任务上对两个最优的VLN模型评估了ILA。结果表明，ILA显著提高了失败率，同时降低了轨迹效率，揭示了VLN智能体对现实室内光照变化的先前未被认识到的脆弱性。我们的代码可在 https://github.com/LiChenyang0820/ILA4VLN 获取。
英文原文摘要 1378 字符
Vision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on perturbations that manifest as unusual textures rarely encountered in everyday indoor environments. Errors under such contrived conditions have limited practical relevance, as real-world agents are unlikely to encounter such artificial patterns. In this work, we focus on indoor lighting, an intrinsic yet largely overlooked scene attribute that strongly influences navigation. We propose Indoor Lighting-based Adversarial Attack (ILA), a black-box framework that manipulates global illumination to disrupt VLN agents. Motivated by typical household lighting usage, we design two attack modes: Static Indoor Lighting-based Attack (SILA), where the lighting intensity remains constant throughout an episode, and Dynamic Indoor Lighting-based Attack (DILA), where lights are switched on or off at critical moments to induce abrupt illumination changes. We evaluate ILA on two state-of-the-art VLN models across three navigation tasks. Results show that ILA significantly increases failure rates while reducing trajectory efficiency, revealing previously unrecognized vulnerabilities of VLN agents to realistic indoor lighting variations. Our code is available at https://github.com/LiChenyang0820/ILA4VLN.