payphone131
payphone131
hi, i also run into the same problem, have you solved it yet?
> I have faced same problem. [@Unispac](https://github.com/Unispac) Please provide guidance to run on liuhaotian/llava-llama-2-13b-chat-lightning-preview model. Thanks Hi, I found the adversarial attack on llava did not improve the ASR (under...
Hello, do you have the dataset? I would appreciate it if you could share the dataset with me.
thanks, your reply really helps.
btw, have you tested the generated adversarial examples on some commercial models? i tested the generated adversarial examples(uncontrained) on GPT-4V, and i found GPT-4V took them as random noisy images...