Maksym Andriushchenko
Maksym Andriushchenko
square-attack
Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]
cross-lipschitz
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation [NeurIPS 2017]
joint-cnn-mrf
Implementation of "Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation"
provable-robustness-max-linear-regions
Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]
provably-robust-boosting
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks [NeurIPS 2019]
relu_networks_overconfident
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]