Yannic Neuhaus's repositories
spurious_imagenet
Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet
auto-attack
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
Language:PythonMIT000
failure-directions
Distilling Model Failures as Directions in Latent Space
Language:Jupyter NotebookMIT000
provably-robust-boosting
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks [NeurIPS 2019]
Language:PythonBSD-3-Clause000