Adversarial Learning

Towards Domain Invariant Single Image Dehazing AAAI 2021 Towards Efficient and Effective Adversarial Training NeurIPS 2021 Towards Evaluating and Training Verifiably Robust Neural Networks CVPR 2021 Towards Extracting Graph Neural Network Models via Prediction Queries (Student Abstract) AAAI 2021 Towards Feature Space Adversarial Attack by Style Perturbation AAAI 2021 Towards Improving Adversarial Training of NLP Models EMNLP 2021 Towards Robust and Reliable Algorithmic Recourse NeurIPS 2021 Towards Robust Classification Model by Counterfactual and Invariant Data Generation CVPR 2021 Towards Robustness of Text-to-SQL Models against Synonym Substitution ACL 2021 Towards Rotation Invariance in Object Detection ICCV 2021 Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration AAAI 2021 Towards Understanding the Generative Capability of Adversarially Robust Classifiers ICCV 2021 Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games NeurIPS 2021 Towards Universal Physical Attacks on Single Object Tracking AAAI 2021 Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling ICML 2021 Training Generative Adversarial Networks in One Stage CVPR 2021 Training Language Models under Resource Constraints for Adversarial Advertisement Detection NAACL 2021 Train simultaneously, generalize better: Stability of gradient-based minimax learners ICML 2021 TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness NeurIPS 2021 Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution ACL 2021 Two-Level Adversarial Visual-Semantic Coupling for Generalized Zero-Shot Learning WACV 2021 UAG: Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks AAAI 2021 Uncertainty-Aware Joint Salient Object and Camouflaged Object Detection CVPR 2021 Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks AAAI 2021 Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability ICML 2021