Sep 2026
Adversarial Attack and Detection in Token‐Pruned Large Vision‐Language Models
An attention‐flip attack that manipulates pruning‐related attention redistribution by suppressing high‐importance visual tokens while promoting low‐importance regions, thereby increasing the likelihood that discriminative visual evidence is discarded during inference is proposed.
Shi-Kai Su, Hui Sun, Le-Feng Zhang
· Concurrency and Computation · 0 citations