← Search

Xuandong Li

2 accepted papers

2022

Wassertrain: An Adversarial Training Framework Against Wasserstein Adversarial Attacks

ICASSP 2022accepted

This paper presents an adversarial training framework WasserTrain for improving model robustness against the adversarial attacks in terms of the Wasserstein distance. First, an effective attack method WasserAttack is introduced with a novel encoding of the optimization problem, which directly finds…

Cited by 0SourceScholar
2021

Testing DNN-based Autonomous Driving Systems under Critical Environmental Conditions

ICML 2021spotlight

Due to the increasing usage of Deep Neural Network (DNN) based autonomous driving systems (ADS) where erroneous or unexpected behaviours can lead to catastrophic accidents, testing such systems is of growing importance. Existing approaches often just focus on finding erroneous behaviours and have no…