Robustness

Feature-Level Debiased Natural Language Understanding AAAI 2023 Fighting Bias With Bias: Promoting Model Robustness by Amplifying Dataset Biases ACL 2023 From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models ACL 2023 Generalist: Decoupling Natural and Robust Generalization CVPR 2023 Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations NeurIPS 2023 GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients NeurIPS 2023 Graph Structure Learning via Lottery Hypothesis at Scale ACML 2023 Hierarchical Randomized Smoothing NeurIPS 2023 H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets NeurIPS 2023 HuaSLIM: Human Attention Motivated Shortcut Learning Identification and Mitigation for Large Language models ACL 2023 Hypothetical Training for Robust Machine Reading Comprehension of Tabular Context ACL 2023 ImageNet Pre-training Also Transfers Non-robustness AAAI 2023 Improving Zero-Shot Generalization and Robustness of Multi-Modal Models CVPR 2023 Introducing Competition To Boost the Transferability of Targeted Adversarial Examples Through Clean Feature Mixup CVPR 2023 Jedi: Entropy-Based Localization and Removal of Adversarial Patches CVPR 2023 LINe: Out-of-Distribution Detection by Leveraging Important Neurons CVPR 2023 Online robust non-stationary estimation NeurIPS 2023 On Private and Robust Bandits NeurIPS 2023 On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection ACL 2023 Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection NeurIPS 2023 Outlier-Robust Gromov-Wasserstein for Graph Data NeurIPS 2023 PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization NeurIPS 2023 PerturbScore: Connecting Discrete and Continuous Perturbations in NLP EMNLP 2023 Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More NeurIPS 2023 Pulling Out All The Full Stops: Punctuation Sensitivity in Neural Machine Translation and Evaluation ACL 2023