| rwightman/pytorch-nips2017-attack-example |
80 |
|
0 |
0 |
over 8 years ago |
0 |
|
3 |
apache-2.0 |
Python |
| A PyTorch baseline attack example for the NIPS 2017 adversarial competition |
| Lab41/cyphercat |
57 |
|
0 |
0 |
over 6 years ago |
0 |
|
15 |
apache-2.0 |
Jupyter Notebook |
| Implementation of membership inference and model inversion attacks, extracting training data information from an ML model. Benchmarking attacks and defenses. |
| P2333/Adaptive-Diversity-Promoting |
39 |
|
0 |
0 |
over 5 years ago |
0 |
|
1 |
apache-2.0 |
Python |
| Adversarial Defense for Ensemble Models (ICML 2019) |
| P2333/Mixup-Inference |
29 |
|
0 |
0 |
almost 6 years ago |
0 |
|
1 |
apache-2.0 |
Python |
| Further improve robustness of mixup-trained models in inference (ICLR 2020) |
| carlini/breaking_defensive_distillation |
20 |
|
0 |
0 |
almost 9 years ago |
0 |
|
0 |
gpl-3.0 |
Python |
| surrealyz/pdfclassifier |
20 |
|
0 |
0 |
over 4 years ago |
0 |
|
1 |
|
Python |
| On Training Robust PDF Malware Classifiers (Usenix Security'20) https://arxiv.org/abs/1904.03542 |
| RicherMans/Speaker-Anti-Spoofing-Classifiers |
14 |
|
0 |
0 |
about 5 years ago |
0 |
|
0 |
|
Python |
| Baselines and Classifiers for speaker anti-spoofing detection |
| mattbev/6.867-final-project |
9 |
|
0 |
0 |
almost 3 years ago |
0 |
|
0 |
mit |
Python |
| Adversarial attacks and defenses against federated learning. |
| ryancampbell514/HeatSmoothing |
6 |
|
0 |
0 |
over 5 years ago |
0 |
|
0 |
|
Python |
| A deterministic approach to Gaussian averaging neural networks |
