50 citations · 136 across the 10 of their papers we have counts for
5 papers · 1 filter
Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
Jiafan He, Dongruo Zhou, Tong Zhang +1
We study the linear contextual bandit problem in the presence of adversarial corruption, where the reward at each round is corrupted by an adversary, and the corruption level (i.e.…
On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
Chen Liu, Zhichao Huang, Mathieu Salzmann +2
Adversarial training is a popular method to robustify models against adversarial attacks. However, it exhibits much more severe overfitting than training on clean inputs. In this w…
CorrAttack: Black-box Adversarial Attack with Structured Search
Zhichao Huang, Yaowei Huang, Tong Zhang
We present a new method for score-based adversarial attack, where the attacker queries the loss-oracle of the target model. Our method employs a parameterized search space with a s…
Black-Box Adversarial Attack with Transferable Model-based Embedding
Zhichao Huang, Tong Zhang
We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a…
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
Yandong Li, Lijun Li, Liqiang Wang +2
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we…