NAT
Collection
A generative adversarial attack targeting low-level neurons for boosting adversarial transferability
•
2 items
•
Updated
Introduction
- We train adversarial generators targeting to disrupt only a specific neuron in the source model. We choose the layer 18 in the VGG16.
- We release 40 generators trained on ImageNet with L2 feature separation loss
Usage
from huggingface_hub import hf_hub_download
import os
# ----------------------------------------------------------------
# to download specfic generator
# ----------------------------------------------------------------
# ----------------------------------------------------------------
# to download all generators
# ----------------------------------------------------------------
repo_id = "KKNakka/NAT"
# 2. Download everything to the ./checkpoints folder
local_dir_path = snapshot_download(
repo_id=repo_id,
local_dir="./checkpoints",
local_dir_use_symlinks=False,
)
print(f"All generators downloaded to: {local_dir_path}")
- Downloads last month
- 3