Adversarial Learning

Residue-Based Natural Language Adversarial Attack Detection NAACL 2022 Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems ICML 2022 Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective NeurIPS 2022 Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation CVPR 2022 Reverse Engineering ℓ_p attacks: A block-sparse optimization approach with recovery guarantees ICML 2022 Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022 Revisiting Non-Parametric Matching Cost Volumes for Robust and Generalizable Stereo Matching NeurIPS 2022 Robust Adversarial Reinforcement Learning with Dissipation Inequation Constraint AAAI 2022 Robust Conversational Agents against Imperceptible Toxicity Triggers NAACL 2022 Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum ICML 2022 Robust Feature-Level Adversaries are Interpretability Tools NeurIPS 2022 Robust Heterogeneous Graph Neural Networks against Adversarial Attacks AAAI 2022 Robust Models Are More Interpretable Because Attributions Look Normal ICML 2022 Robustness and Accuracy Could Be Reconcilable by (Proper) Definition ICML 2022 Robust Optimal Classification Trees against Adversarial Examples AAAI 2022 Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks With Implicit Gradients CVPR 2022 RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining ACL 2022 RoChBert: Towards Robust BERT Fine-tuning for Chinese EMNLP 2022 ROSE: Robust Selective Fine-tuning for Pre-trained Language Models EMNLP 2022 Segment and Complete: Defending Object Detectors Against Adversarial Patch Attacks With Robust Patch Detection CVPR 2022 Semantic-Preserving Adversarial Code Comprehension COLING 2022 Sentence-aware Adversarial Meta-Learning for Few-Shot Text Classification COLING 2022 Shadows Can Be Dangerous: Stealthy and Effective Physical-World Adversarial Attack by Natural Phenomenon CVPR 2022 Shape-Invariant 3D Adversarial Point Clouds CVPR 2022 Shape Prior Guided Attack: Sparser Perturbations on 3D Point Clouds AAAI 2022