microsoft / unadversarialLinks
Official repository for our NeurIPS 2021 paper "Unadversarial Examples: Designing Objects for Robust Vision"
☆105Updated last year
Alternatives and similar repositories for unadversarial
Users that are interested in unadversarial are comparing it to the libraries listed below
Sorting:
- Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs☆97Updated 4 years ago
- A Closer Look at Accuracy vs. Robustness☆88Updated 4 years ago
- Codebase for "Exploring the Landscape of Spatial Robustness" (ICML'19, https://arxiv.org/abs/1712.02779).☆26Updated 5 years ago
- ☆55Updated 5 years ago
- CVPR'19 experiments with (on-manifold) adversarial examples.☆45Updated 5 years ago
- Code for "Testing Robustness Against Unforeseen Adversaries"☆80Updated last year
- Learning perturbation sets for robust machine learning☆65Updated 4 years ago
- ☆141Updated 4 years ago
- Notebooks for reproducing the paper "Computer Vision with a Single (Robust) Classifier"☆128Updated 5 years ago
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆55Updated 3 years ago
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30Updated 3 years ago
- Code for "Learning Perceptually-Aligned Representations via Adversarial Robustness"☆161Updated 5 years ago
- Smooth Adversarial Training☆68Updated 4 years ago
- Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"☆21Updated 3 years ago
- PRIME: A Few Primitives Can Boost Robustness to Common Corruptions☆42Updated 2 years ago
- ☆38Updated 4 years ago
- ☆88Updated last year
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆119Updated 2 years ago
- Trained model weights, training and evaluation code from the paper "A simple way to make neural networks robust against diverse image cor…☆61Updated 2 years ago
- ☆95Updated 2 years ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).