point0bar1 / ebm-defense
PyTorch implementation of BPDA+EOT attack to evaluate adversarial defense with an EBM
☆23Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for ebm-defense
- A Unified Approach to Interpreting and Boosting Adversarial Transferability (ICLR2021)☆28Updated 2 years ago
- SEAT☆20Updated last year
- the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral☆57Updated 3 years ago
- ☆32Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- Code for our NeurIPS 2020 paper Backpropagating Linearly Improves Transferability of Adversarial Examples.☆42Updated last year
- Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off☆29Updated 2 years ago
- ☆19Updated 2 years ago
- ☆55Updated 2 years ago
- CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection☆20Updated 3 years ago
- ReColorAdv and other attacks from the NeurIPS 2019 paper "Functional Adversarial Attacks"☆36Updated 2 years ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆18Updated 2 months ago
- ☆29Updated 2 years ago
- Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks☆37Updated 3 years ago
- ☆22Updated 3 years ago
- [NeurIPS2021] Code Release of Learning Transferable Perturbations☆26Updated 2 years ago
- ☆47Updated last year
- Universal Adversarial Perturbations (UAPs) for PyTorch☆46Updated 3 years ago
- Towards Efficient and Effective Adversarial Training, NeurIPS 2021☆16Updated 2 years ago
- Official repository for "A Self-supervised Approach for Adversarial Robustness" (CVPR 2020--Oral)☆97Updated 3 years ago
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆23Updated last year
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆14Updated last year
- Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.☆18Updated last year
- Code for Boosting fast adversarial training with learnable adversarial initialization (TIP2022)☆29Updated last year
- ☆10Updated 2 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning