microsoft / denoised-smoothing
Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs
☆97Updated 3 years ago
Alternatives and similar repositories for denoised-smoothing:
Users that are interested in denoised-smoothing are comparing it to the libraries listed below
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆52Updated 4 years ago
- Analysis of Adversarial Logit Pairing☆60Updated 6 years ago
- ☆87Updated 7 months ago
- Codebase for "Exploring the Landscape of Spatial Robustness" (ICML'19, https://arxiv.org/abs/1712.02779).☆26Updated 5 years ago
- RayS: A Ray Searching Method for Hard-label Adversarial Attack (KDD2020)☆56Updated 4 years ago
- Code for "Robustness May Be at Odds with Accuracy"☆92Updated last year
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆26Updated 7 months ago
- Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.☆49Updated 5 years ago
- Feature Scattering Adversarial Training (NeurIPS19)☆72Updated 9 months ago
- Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"☆224Updated 5 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆47Updated 2 years ago
- Official implementation for paper: A New Defense Against Adversarial Images: Turning a Weakness into a Strength☆38Updated 5 years ago
- Smooth Adversarial Training☆67Updated 4 years ago
- Source code for the paper "Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness"☆25Updated 5 years ago
- A Closer Look at Accuracy vs. Robustness☆88Updated 3 years ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).☆45Updated 4 years ago
- Semisupervised learning for adversarial robustness https://arxiv.org/pdf/1905.13736.pdf☆140Updated 4 years ago
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆55Updated 3 years ago
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆32Updated 4 years ago
- Code for "Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors"☆63Updated 5 years ago
- Code for the paper "MMA Training: Direct Input Space Margin Maximization through Adversarial Training"☆34Updated 4 years ago
- Understanding and Improving Fast Adversarial Training [NeurIPS 2020]☆95Updated 3 years ago
- Code for Stability Training with Noise (STN)☆21Updated 4 years ago
- Official repository for our NeurIPS 2021 paper "Unadversarial Examples: Designing Objects for Robust Vision"☆103Updated 7 months ago
- ☆156Updated 4 years ago
- Further improve robustness of mixup-trained models in inference (ICLR 2020)☆60Updated 4 years ago
- Benchmark for LP-relaxed robustness verification of ReLU-networks☆41Updated 5 years ago
- Code for "Testing Robustness Against Unforeseen Adversaries"☆81Updated 7 months ago
- [NeurIPS2020] The official repository of "AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows".☆45Updated last year
- Source code for Learning Transferable Adversarial Examples via Ghost Networks (AAAI2020)☆59Updated 6 years ago