works on
adversarial attacks 1black-box optimization 1embodied ai 1gradient-free methods 1vision-language navigation 1

From the 1 of 7 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation

Chenyang Li, Kaige Li, Zeyu Jiang +1

The paper introduces AdvNav, a gradient‑free black‑box adversarial attack that perturbs first‑person visual inputs to disrupt vision‑and‑language navigation agents, using behavior‑…