Adversarial Learning

MaxUp: Lightweight Adversarial Training With Data Augmentation Improves Neural Network Training CVPR 2021 MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation CVPR 2021 Membership Inference Attacks Are Easier on Difficult Problems ICCV 2021 MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding NAACL 2021 Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack ICCV 2021 Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks NeurIPS 2021 Metha: Network Verifiers Need To Be Correct Too! NSDI 2021 MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement Interspeech 2021 MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction ICCV 2021 Mind the Box: l_1-APGD for Sparse Adversarial Attacks on Image Classifiers ICML 2021 Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer EMNLP 2021 Minimal Adversarial Examples for Deep Learning on 3D Point Clouds ICCV 2021 MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps NeurIPS 2021 Mixed Nash Equilibria in the Adversarial Examples Game ICML 2021 Model Agnostic Answer Reranking System for Adversarial Question Answering EACL 2021 Model Extraction and Adversarial Transferability, Your BERT is Vulnerable! NAACL 2021 Model-Targeted Poisoning Attacks with Provable Convergence ICML 2021 Morié Attack (MA): A New Potential Risk of Screen Photos NeurIPS 2021 Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data NeurIPS 2021 MTAAL: Multi-Task Adversarial Active Learning for Medical Named Entity Recognition and Normalization AAAI 2021 Multi-Adversarial Learning for Cross-Lingual Word Embeddings NAACL 2021 Multi-Expert Adversarial Attack Detection in Person Re-Identification Using Context Inconsistency ICCV 2021 Multi-Frame Recurrent Adversarial Network for Moving Object Segmentation WACV 2021 Multi-granularity Textual Adversarial Attack with Behavior Cloning EMNLP 2021 Multi-Layer Random Perturbation Training for improving Model Generalization Efficiently EMNLP 2021