PIP: Detecting Adversarial Examples in Large Vision-Language Models via
Attention Patterns of Irrelevant Probe Questions

PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions

8 September 2024

Yudong Zhang

Xingwu Sun

Papers citing "PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions"

Title
No papers