conftrace_

non-robust feature

8 papers

Explore in graph

Also known as

NRF

Co-occurring keywords · papers mentioning both

adversarial example (5) model robustness (3) adversarial robustness (3) feature learning (3) robust feature (2) adversarial transferability (2) information bottleneck (2) neural network (1) adversarial non-robustness (1) imagenet pre-training (1)

Papers

Adversarial Examples Are Not Real Features NeurIPS 2023 Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently WACV 2023 ImageNet Pre-training Also Transfers Non-robustness AAAI 2023 Can Adversarial Training Be Manipulated By Non-Robust Features? NeurIPS 2022 Improving the Adversarial Robustness of NLP Models by Information Bottleneck ACL 2022 Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective ICCV 2021 Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck NeurIPS 2021 Adversarial Examples Are Not Bugs, They Are Features NeurIPS 2019