Skip to content
conftrace_

robust classification

102 papers

Papers

Towards Building a Robust Toxicity Predictor ACL 2023 Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift UAI 2022 Confidence-based Reliable Learning under Dual Noises NeurIPS 2022 Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them ICML 2022 Distributed adversarial training to robustify deep neural networks at scale UAI 2022 Distributionally robust weighted k-nearest neighbors NeurIPS 2022 Fair Classification with Instance-dependent Label Noise CLeaR 2022 Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation ICML 2022 Improved Generalization Bounds for Adversarially Robust Learning JMLR 2022 Monotonicity regularization: Improved penalties and novel applications to disentangled representation learning and robust classification UAI 2022 Multi-class AUC Optimization for Robust Small-footprint Keyword Spotting with Limited Training Data Interspeech 2022 Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022 Robust High-Dimensional Classification From Few Positive Examples IJCAI 2022 RoLNiP: Robust Learning Using Noisy Pairwise Comparisons ACML 2022 Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022 A Bayes-Optimal View on Adversarial Examples JMLR 2021 Attribute-Guided Adversarial Training for Robustness to Natural Perturbations AAAI 2021 Connecting Interpretability and Robustness in Decision Trees through Separation ICML 2021 Improving Gradient Regularization using Complex-Valued Neural Networks ICML 2021 Learning to Defend by Learning to Attack AISTATS 2021 Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries ICML 2021 Multi-Objective Interpolation Training for Robustness To Label Noise CVPR 2021 On the Hardness of Robust Classification JMLR 2021 Predictive Power of Nearest Neighbors Algorithm under Random Perturbation AISTATS 2021 Provable Robustness of Adversarial Training for Learning Halfspaces with Noise ICML 2021