Huan Zhang

Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTorch).

huanzhang12

Robustness vs Accuracy Survey on ImageNet

huanzhang12

Robust Reinforcement Learning with the Alternating Training of Learned Adversaries (ATLA) framework

huanzhang12

Efficient Robustness Verification for ReLU networks (this repository is outdated, don't use; checkout our new implementation at https://github.com/Verified-Intelligence/auto_LiRPA instead)

huanzhang12

CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is a robustness metric for deep neural networks

huanzhang12

HogWild++: A New Mechanism for Decentralized Asynchronous Stochastic Gradient Descent

huanzhang12

Show-and-Fool: Adversarial Examples for Image Captioning task

huanzhang12

Development Repository for GPU-accelerated GBDT training

huanzhang12

Reference implementations for RecurJac, CROWN, FastLin and FastLip (Neural Network verification and robustness certification algorithms) [Do not use this repo, use https://github.com/Verified-Intelli...

huanzhang12

ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks

huanzhang12