Adversarial Learning

R-AT: Regularized Adversarial Training for Natural Language Understanding EMNLP 2022 Recent improvements of ASR models in the face of adversarial attacks Interspeech 2022 Recursive Reasoning in Minimax Games: A Level k Gradient Play Method NeurIPS 2022 Red Teaming Language Models with Language Models EMNLP 2022 Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off ICLR 2022 RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses Interspeech 2022 Reliable Adversarial Distillation with Unreliable Teachers ICLR 2022 Removing Batch Normalization Boosts Adversarial Training ICML 2022 Research on video adversarial attack with long living cycle UAI 2022 Residue-Based Natural Language Adversarial Attack Detection NAACL 2022 Resilience of Named Entity Recognition Models under Adversarial Attack NAACL 2022 Rethinking Adversarial Transferability from a Data Distribution Perspective ICLR 2022 Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain NeurIPS 2022 Rethinking Deep Face Restoration CVPR 2022 Rethinking Image Restoration for Object Detection NeurIPS 2022 Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems ICML 2022 Rethinking Style Transformer with Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model EMNLP 2022 Rethinking the Reverse-engineering of Trojan Triggers NeurIPS 2022 RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval ICML 2022 RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion Interspeech 2022 Retrospective Adversarial Replay for Continual Learning 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 Reverse Engineering of Imperceptible Adversarial Image Perturbations ICLR 2022 Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022