giladcohen / NNIF_adv_defense
Detection of adversarial examples using influence functions and nearest neighbors
☆32Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for NNIF_adv_defense
- ☆55Updated 2 years ago
- Learnable Boundary Guided Adversarial Training (ICCV2021)☆34Updated last year
- [ICLR 2021] "Robust Overfitting may be mitigated by properly learned smoothening" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, Shiyu Chan…☆46Updated 2 years ago
- Code for our NeurIPS 2020 paper Backpropagating Linearly Improves Transferability of Adversarial Examples.☆42Updated last year
- Adversarial Distributional Training (NeurIPS 2020)☆61Updated 3 years ago
- the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral☆57Updated 3 years ago
- code we used in Decision Boundary Analysis of Adversarial Examples https://openreview.net/forum?id=BkpiPMbA-☆27Updated 6 years ago
- ☆25Updated 5 years ago
- Pytorch implementation of Adversarially Robust Distillation (ARD)☆59Updated 5 years ago
- Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks☆37Updated 3 years ago
- Adversarial Defense for Ensemble Models (ICML 2019)☆61Updated 3 years ago
- Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"☆53Updated 4 years ago
- Code for Black-Box Adversarial Attack with Transferable Model-based Embedding☆57Updated 4 years ago
- Understanding Catastrophic Overfitting in Single-step Adversarial Training [AAAI 2021]☆28Updated 2 years ago
- PyTorch implementations of Adversarial defenses and utils.☆34Updated 10 months ago
- Understanding and Improving Fast Adversarial Training [NeurIPS 2020]☆95Updated 3 years ago
- CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection☆20Updated 3 years ago
- This is the code for semi-supervised robust training (SRT).☆18Updated last year
- Further improve robustness of mixup-trained models in inference (ICLR 2020)☆60Updated 4 years ago
- Code for ICLR2020 "Improving Adversarial Robustness Requires Revisiting Misclassified Examples"☆144Updated 4 years ago
- Feature Scattering Adversarial Training (NeurIPS19)☆71Updated 5 months ago
- ☆40Updated last year
- ATTA (Efficient Adversarial Training with Transferable Adversarial Examples)☆33Updated 4 years ago
- Sparse and Imperceivable Adversarial Attacks (accepted to ICCV 2019).☆40Updated 4 years ago
- Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".☆25Updated 2 years ago
- Improving the Generalization of Adversarial Training with Domain Adaptation☆31Updated 5 years ago
- ☆35Updated 3 years ago
- Universal Adversarial Perturbations (UAPs) for PyTorch☆46Updated 3 years ago
- Codes for reproducing the experimental results in "Proper Network Interpretability Helps Adversarial Robustness in Classification", publi…☆13Updated 4 years ago
- Codes for ICLR 2020 paper "Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets"☆70Updated 4 years ago