249 papers with code • 5 benchmarks • 5 datasets

Adversarial Robustness evaluates the vulnerabilities of machine learning models under various types of adversarial attacks.

# Fixing Data Augmentation to Improve Adversarial Robustness

2 Mar 2021

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.

8,927

7 Oct 2020

In the setting with additional unlabeled data, we obtain an accuracy under attack of 65. 88% against $\ell_\infty$ perturbations of size $8/255$ on CIFAR-10 (+6. 35% with respect to prior art).

8,927

# Are Labels Required for Improving Adversarial Robustness?

Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets than those required for standard classification.

8,927

# Towards Deep Learning Models Resistant to Adversarial Attacks

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.

5,323

3 Jul 2018

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.

2,596

Evaluating adversarial robustness amounts to finding the minimum perturbation needed to have an input sample misclassified.

2,079

# CLAIMED, a visual and scalable component library for Trusted AI

4 Mar 2021

Deep Learning models are getting more and more popular but constraints on explainability, adversarial robustness and fairness are often major concerns for production deployment.

1,304

20 Feb 2019

965

# Feature Denoising for Improving Adversarial Robustness

This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks.

647

# Image Synthesis with a Single (Robust) Classifier

We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis.

Ranked #43 on Image Generation on CIFAR-10 (Inception score metric)

626