Visual-Adversarial-Examples-Jailbreak-Large-Language-Models

Visual-Adversarial-Examples-Jailbreak-Large-Language-Models copied to clipboard

Problem for visual adversarial example bounded by 16/255 on Mini-GPT4

2

Hi, Thank you for sharing the code! It is great that we can reproduce the results on RealToxicityPrompts by using the given images in `adversarial_images`. However, we tried to produce...

chrisyxue

Test on the RealToxicityPrompts Dataset

1

We fed clean.jpeg (panda) into the llava model to calculate the toxic scores and found that there were also 50~60%, do you have the same results

roywang021

Great work, and thanks for sharing the code with us. I noticed that you had added attacking images for both LLaVA and InstructBLIP in the updated paper, however, it seems...

ImKeTT

I hope this message finds you well. My name is Chenhang Cui, and I am currently serving as a research intern at UNC. In the course of our work, we...

gzcch