model robustness

Fighting Bias With Bias: Promoting Model Robustness by Amplifying Dataset Biases ACL 2023 FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-Off Between Accuracy and Robustness WACV 2023 Formalising the Robustness of Counterfactual Explanations for Neural Networks AAAI 2023 Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging ACL 2023 Generative Adversarial Training with Perturbed Token Detection for Model Robustness EMNLP 2023 GeoNet: Benchmarking Unsupervised Adaptation Across Geographies CVPR 2023 How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks ACL 2023 How Many and Which Training Points Would Need to be Removed to Flip this Prediction? EACL 2023 How to Backdoor Diffusion Models? CVPR 2023 HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models ICCV 2023 HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness ICCV 2023 ImageNet Pre-training Also Transfers Non-robustness AAAI 2023 ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations ICLR 2023 Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning ICCV 2023 Improving the Robustness of Summarization Models by Detecting and Removing Input Noise EMNLP 2023 Improving the Robustness of Summarization Systems with Dual Augmentation ACL 2023 Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics ICML 2023 Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning? ICLR 2023 Learning to Ignore Adversarial Attacks EACL 2023 Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation IJCAI 2023 LMentry: A Language Model Benchmark of Elementary Language Tasks ACL 2023 Misleading Relation Classifiers by Substituting Words in Texts ACL 2023 MultiRobustBench: Benchmarking Robustness Against Multiple Attacks ICML 2023 Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation NeurIPS 2023 NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks NeurIPS 2023