Adversarial Learning

InverseNet: Augmenting Model Extraction Attacks with Training Data Inversion IJCAI 2021 Inverting Generative Adversarial Renderer for Face Reconstruction CVPR 2021 Investigating Robustness of Dialog Models to Popular Figurative Language Constructs EMNLP 2021 Investigating vulnerabilities of deep neural policies UAI 2021 Invisible Backdoor Attack With Sample-Specific Triggers ICCV 2021 Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effect CVPR 2021 IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking CVPR 2021 IR-GAN: Room Impulse Response Generator for Far-Field Speech Recognition Interspeech 2021 IRM—when it works and when it doesn't: A test case of natural language inference NeurIPS 2021 ITNLP at SemEval-2021 Task 11: Boosting BERT with Sampling and Adversarial Training for Knowledge Extraction SemEval 2021 Just One Moment: Structural Vulnerability of Deep Action Recognition Against One Frame Attack ICCV 2021 Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction EMNLP 2021 Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks ICML 2021 Knowledge-Enriched Distributional Model Inversion Attacks ICCV 2021 KnowMAN: Weakly Supervised Multinomial Adversarial Networks EMNLP 2021 Label-Only Membership Inference Attacks ICML 2021 LAFEAT: Piercing Through Adversarial Defenses With Latent Features CVPR 2021 Large Norms of CNN Layers Do Not Hurt Adversarial Robustness AAAI 2021 Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection NAACL 2021 Learnable Boundary Guided Adversarial Training ICCV 2021 Learning and certification under instance-targeted poisoning UAI 2021 Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization ICCV 2021 Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning EACL 2021 Learning Diverse-Structured Networks for Adversarial Robustness ICML 2021 Learning Fast Converging, Effective Conditional Generative Adversarial Networks With a Mirrored Auxiliary Classifier WACV 2021