Adversarial Defense
Leaderboards
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
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
The Limitations of Deep Learning in Adversarial Settings
In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs.
Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
Based on this observation, we propose a defense approach which inspects the graph and recovers the potential adversarial perturbations.
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.
Feature Denoising for Improving Adversarial Robustness
CVPR 2019
• facebookresearch/ImageNet-Adversarial-Training
•
This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks.
SOTA for Adversarial Defense on CAAD 2018
advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch
advertorch is a toolbox for adversarial robustness research.
SOTA for Adversarial Attack on 1B Words (using extra training data)
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.
Towards Deep Learning Models Resistant to Adversarial Attacks
ICLR 2018
• MadryLab/mnist_challenge
•
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.
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.
On Evaluating Adversarial Robustness
• evaluating-adversarial-robustness/adv-eval-paper
•
Correctly evaluating defenses against adversarial examples has proven to be extremely difficult.