Adversarial Defense
State-of-the-art leaderboards
Greatest papers with code
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
ICML 2018 • anishathalye/obfuscated-gradients
We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples.
Countering Adversarial Images using Input Transformations
ICLR 2018
• facebookresearch/adversarial_image_defenses
• 
This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system.
Feature Denoising for Improving Adversarial Robustness
• facebookresearch/ImageNet-Adversarial-Training
This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks.
Towards Deep Learning Models Resistant to Adversarial Attacks
ICLR 2018
• MadryLab/mnist_challenge
• 
Recent work has demonstrated that neural networks are vulnerable to adversarial examples, i. e., inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network.
advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch
advertorch is a toolbox for adversarial robustness research.
A Provable Defense for Deep Residual Networks
• eth-sri/diffai
•
We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100.
Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
CVPR 2018 • lfz/Guided-Denoise
First, with HGD as a defense, the target model is more robust to either white-box or black-box adversarial attacks.
On Evaluating Adversarial Robustness
• evaluating-adversarial-robustness/adv-eval-paper
•
Correctly evaluating defenses against adversarial examples has proven to be extremely difficult.
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
ICLR 2019
• hendrycks/robustness
•
Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.