RobustBench
A standardized benchmark for adversarial robustness

The goal of RobustBench is to systematically track the real progress in adversarial robustness. There are already more than 3'000 papers on this topic, but it is still unclear which approaches really work and which only lead to overestimated robustness. We start from benchmarking common corruptions, $$\ell_\infty$$- and $$\ell_2$$-robustness since these are the most studied settings in the literature. We use AutoAttack, an ensemble of white-box and black-box attacks, to standardize the evaluation (for details see our paper) of the $$\ell_p$$ robustness and CIFAR-10-C for the evaluation of robustness to common corruptions. Additionally, we open source the RobustBench library that contains models used for the leaderboard to facilitate their usage for downstream applications.

To prevent potential overadaptation of new defenses to AutoAttack, we also welcome external evaluations based on adaptive attacks, especially where AutoAttack flags a potential overestimation of robustness. For each model, we are interested in the best known robust accuracy and see AutoAttack and adaptive attacks as complementary.

on 120+ models

robust models via Model Zoo

Model Zoo

Check out the available models and our Colab tutorials.
# !pip install git+https://github.com/RobustBench/robustbench@v0.2.1
# Load a model from the model zoo
dataset='cifar10',
threat_model='Linf')

# Evaluate the Linf robustness of the model using AutoAttack
from robustbench.eval import benchmark
clean_acc, robust_acc = benchmark(model,
dataset='cifar10',
threat_model='Linf')


Analysis

Check out our paper with a detailed analysis.

Leaderboard: CIFAR-10, $$\ell_\infty = 8/255$$, untargeted attack

1
1
1
1
Leaderboard: CIFAR-10, $$\ell_2 = 0.5$$, untargeted attack

1
1
1
1

1
1
1
1
Leaderboard: CIFAR-100, $$\ell_\infty = 8/255$$, untargeted attack

1
1
1
1

1
1
1
1
Leaderboard: ImageNet, $$\ell_\infty = 4/255$$, untargeted attack

1
1
1
1

FAQ

➤ How does the RobustBench leaderboard differ from the AutoAttack leaderboard? 🤔
The AutoAttack leaderboard was the starting point of RobustBench. Now only the RobustBench leaderboard is actively maintained.

➤ How does the RobustBench leaderboard differ from robust-ml.org? 🤔
robust-ml.org focuses on adaptive evaluations, but we provide a standardized benchmark. Adaptive evaluations have been very useful (e.g., see Tramer et al., 2020), but they are also very time-consuming and cannot be standardized by definition. Instead, we argue that one can estimate robustness accurately mostly without adaptive attacks but for this one has to introduce some restrictions on the considered models (see our paper for more details). However, we do welcome adaptive evaluations and we are always interested in showing the best known robust accuracy.

➤ How is it related to libraries like foolbox / cleverhans / advertorch? 🤔
These libraries provide implementations of different attacks. Besides the standardized benchmark, RobustBench additionally provides a repository of the most robust models. So you can start using the robust models in one line of code (see the tutorial here).

➤ Why is Lp-robustness still interesting in 2021? 🤔
There are numerous interesting applications of Lp-robustness that span transfer learning (Salman et al. (2020), Utrera et al. (2020)), interpretability (Tsipras et al. (2018), Kaur et al. (2019), Engstrom et al. (2019)), security (Tramèr et al. (2018), Saadatpanah et al. (2019)), generalization (Xie et al. (2019), Zhu et al. (2019), Bochkovskiy et al. (2020)), robustness to unseen perturbations (Xie et al. (2019), Kang et al. (2019)), stabilization of GAN training (Zhong et al. (2020)).

We mostly focus on defenses which improve empirical robustness, given the lack of clarity regarding which approaches really improve robustness and which only make some particular attacks unsuccessful. However, we do not restrict submissions of verifiably robust models (e.g., we have Zhang et al. (2019) in our CIFAR-10 Linf leaderboard). For methods targeting verified robustness, we encourage the readers to check out Salman et al. (2019) and Li et al. (2020).

➤ What if I have a better attack than the one used in this benchmark? 🤔
We will be happy to add a better attack or any adaptive evaluation that would complement our default standardized attacks!

Citation

Consider citing our whitepaper if you want to reference our leaderboard or if you are using the models from the Model Zoo:
@article{croce2020robustbench,
title={RobustBench: a standardized adversarial robustness benchmark},
author={Croce, Francesco and Andriushchenko, Maksym and Sehwag, Vikash and Debenedetti, Edoardo and Flammarion, Nicolas
and Chiang, Mung and Mittal, Prateek and Matthias Hein},
journal={arXiv preprint arXiv:2010.09670},
year={2020}
}

Contribute to RobustBench!

We welcome any contribution in terms of both new robust models and evaluations. Please check here for more details.