Adversarial Learning

Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks AAAI 2022 Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators ICLR 2022 Privacy-Preserving Face Recognition in the Frequency Domain AAAI 2022 Proactive Image Manipulation Detection CVPR 2022 Probing Script Knowledge from Pre-Trained Models EMNLP 2022 Probing the Robustness of Trained Metrics for Conversational Dialogue Systems ACL 2022 Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-Robust Makeup Transfer CVPR 2022 Pyramid Adversarial Training Improves ViT Performance CVPR 2022 Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets NeurIPS 2022 Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks NeurIPS 2022 Random Normalization Aggregation for Adversarial Defense NeurIPS 2022 R-AT: Regularized Adversarial Training for Natural Language Understanding EMNLP 2022 RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses Interspeech 2022 Removing Batch Normalization Boosts Adversarial Training 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 Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation CVPR 2022 Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text Generation ACL 2022 RGB-Depth Fusion GAN for Indoor Depth Completion CVPR 2022 Robust Heterogeneous Graph Neural Networks against Adversarial Attacks AAAI 2022 Robust Lottery Tickets for Pre-trained Language Models ACL 2022 Robust Models are less Over-Confident NeurIPS 2022 Robustness and Accuracy Could Be Reconcilable by (Proper) Definition ICML 2022 Robustness Disparities in Face Detection NeurIPS 2022 Robust Optimization As Data Augmentation for Large-Scale Graphs CVPR 2022