Adversarial Learning

SPSG: Self-Supervised Photometric Scene Generation From RGB-D Scans CVPR 2021 Stable Adversarial Learning under Distributional Shifts AAAI 2021 Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks NeurIPS 2021 StarGAN-VC+ASR: StarGAN-Based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition Interspeech 2021 Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations AAAI 2021 StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding AAAI 2021 Style-Based Point Generator With Adversarial Rendering for Point Cloud Completion CVPR 2021 StyleMix: Separating Content and Style for Enhanced Data Augmentation CVPR 2021 Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images AAAI 2021 SurfGen: Adversarial 3D Shape Synthesis With Explicit Surface Discriminators ICCV 2021 SurFree: A Fast Surrogate-Free Black-Box Attack CVPR 2021 Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation EMNLP 2021 TAG: Gradient Attack on Transformer-based Language Models EMNLP 2021 Task-Aware Variational Adversarial Active Learning CVPR 2021 Teacher-Student Adversarial Depth Hallucination To Improve Face Recognition ICCV 2021 TextGAIL: Generative Adversarial Imitation Learning for Text Generation AAAI 2021 The Translucent Patch: A Physical and Universal Attack on Object Detectors CVPR 2021 Token-Aware Virtual Adversarial Training in Natural Language Understanding AAAI 2021 Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons ICML 2021 Towards Evaluating and Training Verifiably Robust Neural Networks CVPR 2021 Towards Feature Space Adversarial Attack by Style Perturbation AAAI 2021 Towards Improving Adversarial Training of NLP Models EMNLP 2021 Towards Rotation Invariance in Object Detection ICCV 2021 Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration AAAI 2021 Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling ICML 2021