most citedCausal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Network

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2022★ 1 cited

Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Network

Huan Hua, Jun Yan, Xi Fang +3

The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning. However, this method suffers from the spurious correlation, whic…