microsoft / unadversarial
Official repository for our NeurIPS 2021 paper "Unadversarial Examples: Designing Objects for Robust Vision"
☆103Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for unadversarial
- Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs☆96Updated 3 years ago
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆54Updated 2 years ago
- Codebase for "Exploring the Landscape of Spatial Robustness" (ICML'19, https://arxiv.org/abs/1712.02779).☆26Updated 5 years ago
- Understanding and Improving Fast Adversarial Training [NeurIPS 2020]☆94Updated 3 years ago
- ☆55Updated 4 years ago
- A Closer Look at Accuracy vs. Robustness☆87Updated 3 years ago
- Smooth Adversarial Training☆67Updated 3 years ago
- Official implementation for paper: A New Defense Against Adversarial Images: Turning a Weakness into a Strength☆37Updated 4 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆25Updated 3 months ago
- ☆138Updated 4 years ago
- Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"☆223Updated 5 years ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).☆45Updated 4 years ago
- ☆22Updated 2 years ago
- Code for the paper "Understanding Generalization through Visualizations"☆60Updated 3 years ago
- [NeurIPS'21] "AugMax: Adversarial Composition of Random Augmentations for Robust Training" by Haotao Wang, Chaowei Xiao, Jean Kossaifi, Z…☆124Updated 2 years ago
- Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks, in ICCV 2019☆59Updated 5 years ago
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30Updated 2 years ago
- Code for "Testing Robustness Against Unforeseen Adversaries"☆80Updated 3 months ago
- Official repo for the paper "Make Some Noise: Reliable and Efficient Single-Step Adversarial Training" (https://arxiv.org/abs/2202.01181)☆25Updated 2 years ago
- [NeurIPS2020] The official repository of "AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows".☆45Updated last year
- ☆37Updated 9 months ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆46Updated last year
- Learning perturbation sets for robust machine learning☆64Updated 3 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆50Updated 4 years ago
- Visualization of Adversarial Examples☆32Updated 6 years ago
- ☆96Updated 2 years ago
- This repository provides code for "On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness".☆44Updated 2 years ago
- A framework for analyzing computer vision models with simulated data☆124Updated 3 years ago
- PRIME: A Few Primitives Can Boost Robustness to Common Corruptions☆42Updated last year