Adversarial Robustness

249 papers with code • 5 benchmarks • 5 datasets

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

Greatest papers with code

Fixing Data Augmentation to Improve Adversarial Robustness

deepmind/deepmind-research 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.

Adversarial Robustness Data Augmentation

Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples

deepmind/deepmind-research 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).

Adversarial Robustness

Are Labels Required for Improving Adversarial Robustness?

deepmind/deepmind-research NeurIPS 2019

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.

Adversarial Robustness

Towards Deep Learning Models Resistant to Adversarial Attacks

tensorflow/cleverhans 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.

Adversarial Attack Adversarial Defense +4

Adversarial Robustness Toolbox v1.0.0

IBM/adversarial-robustness-toolbox 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.

Adversarial Robustness Gaussian Processes +1

Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints

bethgelab/foolbox NeurIPS 2021

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

Adversarial Attack Adversarial Robustness

CLAIMED, a visual and scalable component library for Trusted AI

IBM/claimed 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.

Adversarial Robustness Fairness

Image Synthesis with a Single (Robust) Classifier

MadryLab/robustness NeurIPS 2019

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)

Adversarial Robustness Image Generation