README.md

---
license: apache-2.0
datasets:
- ILSVRC/imagenet-1k
language:
- en
pipeline_tag: image-to-image
tags:
- advgenerators
---
<div align="center">

<a href="https://krishnakanthnakka.github.io/NAT/"><img src="https://img.shields.io/badge/Project-Page-blue?style=for-the-badge&logo=googlechrome&logoColor=white"></a>
<a href="https://github.com/krishnakanthnakka/NAT.git"><img src="https://img.shields.io/badge/GitHub-Repository-black?style=for-the-badge&logo=github&logoColor=white"></a>
<a href="https://arxiv.org/pdf/2508.16937"><img src="https://img.shields.io/badge/Arxiv-2508.16937-red?style=for-the-badge&logo=arxiv&logoColor=white"></a>
<a href="https://huggingface.co/KKNakka/NAT"><img src="https://img.shields.io/badge/Hugging%20Face-Model-yellow?style=for-the-badge&logo=huggingface&logoColor=black"></a>
<a href="https://openaccess.thecvf.com/content/WACV2025/papers/Nakka_NAT_Learning_to_Attack_Neurons_for_Enhanced_Adversarial_Transferability_WACV_2025_paper.pdf"><img src="https://img.shields.io/badge/WACV-2025-blue?style=for-the-badge"></a>

</div>



## 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

```py


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}")

```