Sep 2026
Adversarial Attack and Detection in Token‐Pruned Large Vision‐Language Models
Large vision‐language models (LVLMs) incur high computational costs, and visual token pruning is commonly used to remove redundant tokens and enhance efficiency. However, from a security perspective, such acceleration mechanisms may have a non‐monotonic impact on adversarial robustness: They may either improve robust...
Shi-Kai Su, Hui Sun, Le-Feng Zhang
· Concurrency and Computation · 0 citations