Maksym Andriushchenko

Results 6 repositories owned by Maksym Andriushchenko

square-attack

143
Stars
26
Forks
Watchers

Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]

cross-lipschitz

19
Stars
3
Forks
Watchers

Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation [NeurIPS 2017]

joint-cnn-mrf

49
Stars
17
Forks
Watchers

Implementation of "Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation"

Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]

provably-robust-boosting

49
Stars
11
Forks
Watchers

Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks [NeurIPS 2019]

relu_networks_overconfident

177
Stars
20
Forks
Watchers

Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]