Harry24k / catastrophic-overfitting
Understanding Catastrophic Overfitting in Single-step Adversarial Training [AAAI 2021]
☆27Updated 2 years ago
Related projects: ⓘ
- Code for our NeurIPS 2020 paper Backpropagating Linearly Improves Transferability of Adversarial Examples.☆42Updated last year
- ☆55Updated 2 years ago
- Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"☆52Updated 3 years ago
- ☆41Updated last year
- Code for CVPR2020 paper QEBA: Query-Efficient Boundary-Based Blackbox Attack☆30Updated 3 years ago
- Sparse and Imperceivable Adversarial Attacks (accepted to ICCV 2019).☆40Updated 3 years ago
- Code for ICLR2020 "Improving Adversarial Robustness Requires Revisiting Misclassified Examples"☆143Updated 3 years ago
- ATTA (Efficient Adversarial Training with Transferable Adversarial Examples)☆32Updated 4 years ago
- A pytorch implementation of "Ensemble Adversarial Training : Attacks and Defenses"☆9Updated 5 years ago
- A PyTorch Implementation of the UAP attack☆19Updated 5 years ago
- Learnable Boundary Guided Adversarial Training (ICCV2021)☆33Updated last year
- Codes for ICLR 2020 paper "Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets"☆70Updated 3 years ago
- PyTorch implementations of Adversarial defenses and utils.☆34Updated 8 months ago
- Pytorch code for ens_adv_train☆15Updated 5 years ago
- Repository for Certified Defenses for Adversarial Patch ICLR-2020☆32Updated 4 years ago
- code we used in Decision Boundary Analysis of Adversarial Examples https://openreview.net/forum?id=BkpiPMbA-☆27Updated 5 years ago
- Strongest attack against Feature Scatter and Adversarial Interpolation☆25Updated 4 years ago
- Adversarial Distributional Training (NeurIPS 2020)☆61Updated 3 years ago
- A pytorch implementation of "Towards Evaluating the Robustness of Neural Networks"☆52Updated 5 years ago
- Detection of adversarial examples using influence functions and nearest neighbors☆32Updated last year
- Adversarial attacks including DeepFool and C&W☆13Updated 5 years ago
- The code of ICCV2021 paper "Meta Gradient Adversarial Attack"☆22Updated 2 years ago
- Understanding and Improving Fast Adversarial Training [NeurIPS 2020]☆94Updated 2 years ago
- Codes for reproducing the experimental results in "Proper Network Interpretability Helps Adversarial Robustness in Classification", publi…☆13Updated 4 years ago
- Code for Black-Box Adversarial Attack with Transferable Model-based Embedding☆55Updated 4 years ago
- ☆13Updated 4 years ago
- ☆76Updated 3 years ago
- ConvexPolytopePosioning☆33Updated 4 years ago
- Official repository for "Cross-Domain Transferability of Adversarial Perturbations" (NeurIPS 2019)☆57Updated 3 years ago
- The implementation of our paper: Composite Adversarial Attacks (AAAI2021)☆30Updated 2 years ago