adversarial robustness

Adversarial Robustness in Multi-Task Learning: Promises and Illusions AAAI 2022 Adversarial Robustness is at Odds with Lazy Training NeurIPS 2022 Adversarial Robustness of Deep Sensor Fusion Models WACV 2022 Adversarial Robustness Through the Lens of Causality ICLR 2022 A Dynamical System Perspective for Lipschitz Neural Networks ICML 2022 Approximate Exploitability: Learning a Best Response IJCAI 2022 A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits NeurIPS 2022 Assaying Out-Of-Distribution Generalization in Transfer Learning NeurIPS 2022 A Study of the Attention Abnormality in Trojaned BERTs NAACL 2022 A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective NeurIPS 2022 A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space IJCAI 2022 A Unified Wasserstein Distributional Robustness Framework for Adversarial Training ICLR 2022 Automatic Fake News Detection: Are current models “fact-checking” or“gut-checking”? ACL 2022 A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction NAACL 2022 Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense ICML 2022 Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint ICML 2022 Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations EMNLP 2022 Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness NeurIPS 2022 Building Robust Ensembles via Margin Boosting ICML 2022 Can Rationalization Improve Robustness? NAACL 2022 Can we Generalize and Distribute Private Representation Learning? AISTATS 2022 CAT: Customized Adversarial Training for Improved Robustness IJCAI 2022 CC-CERT: A Probabilistic Approach to Certify General Robustness of Neural Networks AAAI 2022 Certifiably Robust Variational Autoencoders AISTATS 2022 Certified Adversarial Robustness Under the Bounded Support Set ICML 2022