7 results found Sort:
- Filter by Primary Language:
- Python (6)
- Jupyter Notebook (1)
- +
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models....
Created
2018-08-08
378 commits to master branch, last one 2 years ago
A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.
Created
2020-03-19
190 commits to main branch, last one about a year ago
Implementation of Papers on Adversarial Examples
Created
2018-01-27
24 commits to master branch, last one about a year ago
Detection by Attack: Detecting Adversarial Samples by Undercover Attack
Created
2019-05-14
47 commits to master branch, last one 4 years ago
Implementation of gradient-based adversarial attack(FGSM,MI-FGSM,PGD)
Created
2021-06-04
14 commits to master branch, last one 3 years ago
SHIELD: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
Created
2018-02-05
63 commits to master branch, last one 6 years ago
The first real-world adversarial attack on MTCNN face detetction system to date
Created
2019-10-14
8 commits to master branch, last one 3 years ago