Adversarial Learning

AugMax: Adversarial Composition of Random Augmentations for Robust Training NeurIPS 2021 Augmented Lagrangian Adversarial Attacks ICCV 2021 Augmenting Imbalanced Time-series Data via Adversarial Perturbation in Latent Space ACML 2021 A Unified Approach to Interpreting and Boosting Adversarial Transferability ICLR 2021 A Unified Multi-Scenario Attacking Network for Visual Object Tracking AAAI 2021 A Universal Multi-Speaker Multi-Style Text-to-Speech via Disentangled Representation Learning Based on Rényi Divergence Minimization Interspeech 2021 Automated Discovery of Adaptive Attacks on Adversarial Defenses NeurIPS 2021 Automatic Object Recoloring Using Adversarial Learning WACV 2021 AVA: Adversarial Vignetting Attack against Visual Recognition IJCAI 2021 Average-case Acceleration for Bilinear Games and Normal Matrices ICLR 2021 Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning EMNLP 2021 Backdoor Attack with Imperceptible Input and Latent Modification NeurIPS 2021 BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning IJCAI 2021 Bag of Tricks for Adversarial Training ICLR 2021 Bandit Learning in Decentralized Matching Markets JMLR 2021 BASAR:Black-Box Attack on Skeletal Action Recognition CVPR 2021 Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective ICCV 2021 BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text Classification NAACL 2021 Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions AAAI 2021 BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks ACL 2021 BESA: BERT-based Simulated Annealing for Adversarial Text Attacks IJCAI 2021 Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning Interspeech 2021 Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training NeurIPS 2021 Beyond Max-Margin: Class Margin Equilibrium for Few-Shot Object Detection CVPR 2021 BFClass: A Backdoor-free Text Classification Framework EMNLP 2021