Welcome to ARES’s documentation!

Installation

Before start, please first install ARES 2.0 as follows:

• Initialize a dedicated environment for ARES 2.0.

conda create -n ares python==3.10.9
conda activate ares

• Clone and setup:

git clone https://github.com/thu-ml/ares2.0
cd ares2.0
pip install -r requirements.txt
mim install mmengine==0.8.4
mim install mmcv==2.0.0
mim install mmdet==3.1.0
pip install -v -e .

Tutorials

• Attacking Image Classification Models
• Attacking Object Detection Models
• Robust Training for Image Classification

API Docs

• ares.attack package
• ares.attack.detection package
• ares.defense package
• ares.dataset package
• ares.model package
• ares.utils package

Indices and tables

• Index

• Module Index

• Search Page