Ping-C / certifiedpatchdefenseLinks
Repository for Certified Defenses for Adversarial Patch ICLR-2020
☆34Updated 5 years ago
Alternatives and similar repositories for certifiedpatchdefense
Users that are interested in certifiedpatchdefense are comparing it to the libraries listed below
Sorting:
- Code for "On Adaptive Attacks to Adversarial Example Defenses"☆86Updated 4 years ago
- Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"☆53Updated 4 years ago
- ☆60Updated 3 years ago
- Code for our NeurIPS 2020 paper Backpropagating Linearly Improves Transferability of Adversarial Examples.☆42Updated 2 years ago
- ☆86Updated 4 years ago
- ☆41Updated 2 years ago
- Sparse and Imperceivable Adversarial Attacks (accepted to ICCV 2019).☆41Updated 4 years ago
- Code for ICLR2020 "Improving Adversarial Robustness Requires Revisiting Misclassified Examples"☆151Updated 4 years ago
- Code for CVPR2020 paper QEBA: Query-Efficient Boundary-Based Blackbox Attack☆32Updated 4 years ago
- ☆56Updated 2 years ago
- Attacks Which Do Not Kill Training Make Adversarial Learning Stronger (ICML2020 Paper)☆126Updated 2 years ago
- The implementation of our paper: Composite Adversarial Attacks (AAAI2021)☆30Updated 3 years ago
- ATTA (Efficient Adversarial Training with Transferable Adversarial Examples)☆36Updated 5 years ago
- Adversarial Distributional Training (NeurIPS 2020)☆63Updated 4 years ago
- Universal Adversarial Perturbations (UAPs) for PyTorch☆49Updated 4 years ago
- Code for the paper "(De)Randomized Smoothing for Certifiable Defense against Patch Attacks" by Alexander Levine and Soheil Feizi.☆17Updated 3 years ago
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆56Updated 3 years ago
- Code for "Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors"☆64Updated 5 years ago
- Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]☆168Updated 5 years ago
- Code for Black-Box Adversarial Attack with Transferable Model-based Embedding☆58Updated 5 years ago
- Implementation of our ICLR 2021 paper: Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples.☆11Updated 4 years ago
- Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".☆24Updated 3 years ago
- Paper sharing in adversary related works☆44Updated last month
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching☆110Updated last year
- A pytorch implementation of "Towards Evaluating the Robustness of Neural Networks"☆59Updated 6 years ago
- Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks☆39Updated 4 years ago
- Code for "PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier"☆42Updated 2 years ago
- Code for "Adversarial Camouflage: Hiding Physical World Attacks with Natural Styles" (CVPR 2020)☆94Updated 2 years ago
- Codes for ICLR 2020 paper "Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets"☆70Updated 4 years ago
- Defending Against Physically Realizable Attacks on Image Classification☆35Updated 3 years ago