Adversarial Robustness
603 papers with code • 7 benchmarks • 9 datasets
Adversarial Robustness evaluates the vulnerabilities of machine learning models under various types of adversarial attacks.
Benchmarks
These leaderboards are used to track progress in Adversarial Robustness
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Adversarial Robustness models and implementationsDatasets
CIFAR-10
ImageNet
CIFAR-100
ImageNet-C
ImageNet-A
Stylized ImageNet
AdvGLUE
ImageNet-Patch
Most implemented papers
Towards Deep Learning Models Resistant to Adversarial Attacks
MadryLab/mnist_challenge
•
•
ICLR 2018
Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.
Generating Adversarial Examples with Adversarial Networks
MadryLab/mnist_challenge
•
•
ICLR 2018
A challenge to explore adversarial robustness of neural networks on MNIST.
Certified Adversarial Robustness via Randomized Smoothing
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm.
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
fra31/auto-attack
•
•
ICML 2020
The field of defense strategies against adversarial attacks has significantly grown over the last years, but progress is hampered as the evaluation of adversarial defenses is often insufficient and thus gives a wrong impression of robustness.
Theoretically Principled Trade-off between Robustness and Accuracy
yaodongyu/TRADES
•
•
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples.
Robustness May Be at Odds with Accuracy
louis2889184/pytorch-adversarial-training
•
•
ICLR 2019
We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization.
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify.
Improving Adversarial Robustness via Promoting Ensemble Diversity
P2333/Adaptive-Diversity-Promoting
•
•
Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks.
Fixing Data Augmentation to Improve Adversarial Robustness
deepmind/deepmind-research
•
•
In particular, against $\ell_\infty$ norm-bounded perturbations of size $\epsilon = 8/255$, our model reaches 64. 20% robust accuracy without using any external data, beating most prior works that use external data.
Adversarial Robustness Toolbox v1.0.0
IBM/adversarial-robustness-toolbox
•
•
Defending Machine Learning models involves certifying and verifying model robustness and model hardening with approaches such as pre-processing inputs, augmenting training data with adversarial samples, and leveraging runtime detection methods to flag any inputs that might have been modified by an adversary.
