Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack

This paper studies the robustness of vision-and-language navigation (VLN) agents through an indoor lighting-based adversarial attack. By perturbing realistic illumination conditions in indoor environments, the work exposes vulnerabilities of embodied navigation policies to naturally occurring visual shifts that conventional adversarial benchmarks overlook.

Authors: Chenyang Li, Wenbing Tang, Yihao Huang, Sinong Simon Zhan, Ming Hu, Xiaojun Jia, Yang Liu

@inproceedings{li2026shedding, title={Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack}, author={Li, Chenyang and Tang, Wenbing and Huang, Yihao and Zhan, Sinong Simon and Hu, Ming and Jia, Xiaojun and Liu, Yang}, booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2026}, url={https://arxiv.org/abs/2511.13132} }