Pinned Loading

1. bethgelab/foolbox bethgelab/foolbox Public

   A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

   Python 2.9k 432

2. brendel-group/causal-understanding-via-visualizations brendel-group/causal-understanding-via-visualizations Public

   Official repository for the paper "How Well do Feature Visualizations Support Causal Understanding of CNN Activations?".

   JavaScript 9 3

3. brendel-group/cl-ica brendel-group/cl-ica Public

   Code for the paper "Contrastive Learning Inverts the Data Generating Process".

   Python 90 11

4. bethgelab/testing_visualizations bethgelab/testing_visualizations Public archive

   Code for the paper " Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations"

   Python 10 2

5. shift-happens-benchmark/icml-2022 shift-happens-benchmark/icml-2022 Public

   Crowdsourcing metrics and test datasets beyond ImageNet (ICML 2022 workshop)

   Python 38 17

6. google-research/active-adversarial-tests google-research/active-adversarial-tests Public

   Official implementation of the paper "Increasing Confidence in Adversarial Robustness Evaluations"

   Python 18 3