-
Hi Lei,
I just came across your RIBLT paper and for the most part I thought it was compelling and clear, and the scheme described has tremendous potential. However, I believe it contains a misunder…
-
The expert/solver agent should be an agent that uses the following:
- chain of thought reasoning
- system 2 thinking
- verify step by step
- reflection
This agent will be pitted in an adversa…
-
Hello,
In Table 5 of your paper _"AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models"_, you mentioned the experiments are done on the ImageNet dataset. I wonder if it is …
-
Hi author,
When I was reproducing the code, I found that after saving the attacked adversarial examples, there was a significant difference between the attacked adversarial samples and the original i…
-
Hi, I ran the scripts provided in this github repo but faced multiple issues:
**Issue 1: Cannot reproduce the paper results**
In Table 4 of the paper, it is mentioned that the word level perturbat…
-
Title & author list on [anthology page](https://aclanthology.org/2024.acl-tutorials.5/):
* Vulnerabilities of Large Language Models to Adversarial Attacks
* Yu Fu, Erfan Shayegan, Md. Mamun Al Abdul…
-
Hi,
I'm interested in attacking yolov8 to test methods for better resistance.
The yolo model is not accepted in torchattacks. Instead, I tried to import and attack a pre-implemented model from t…
-
## Issue
The task is to formulate non-SFT attacks in order to test the robustness of a defence solution.
The attack will need to run with an arbitrary domain like medical advice.
Types of Attac…
-
hello i found that in your code you save images as '.bmp'. i changed the code to save images as '.jpg' and found minigpt4 said the saved adversarial images are blurred and pixelated, which suggests th…
-
Hi, I just tried to have the cyclic-adv-s545 model play against the latest 28b model. However, it doesn't seem to work very well. And I would like to do some fine tuning on my own. I just saw some scr…