2 open source projects by advboxes

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. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

✭ 1,055

jupyter-notebook deep-learning machine-learning security onnx

2. perceptron-benchmark

Robustness benchmark for DNN models.

✭ 61

python security benchmarking adversarial-machine-learning

1-2 of 2 user projects