research
∙
06/15/2022
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
The AutoAttack (AA) has been the most reliable method to evaluate advers...
share
research
∙
10/06/2021
Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem
Existing deep reinforcement learning (DRL) based methods for solving the...
research
∙
06/30/2021
Local Reweighting for Adversarial Training
Instances-reweighted adversarial training (IRAT) can significantly boost...
research
∙
10/22/2020
Maximum Mean Discrepancy is Aware of Adversarial Attacks
The maximum mean discrepancy (MMD) test, as a representative two-sample ...
research
∙
10/10/2019