Adversarial Learning

Gradient-based Adversarial Attacks against Text Transformers EMNLP 2021 Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization EMNLP 2021 Gradient Distribution Alignment Certificates Better Adversarial Domain Adaptation ICCV 2021 Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering NeurIPS 2021 Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models IJCAI 2021 Grenzlinie at SemEval-2021 Task 7: Detecting and Rating Humor and Offense SemEval 2021 Grey-box Adversarial Attack And Defence For Sentiment Classification NAACL 2021 Group Softmax Loss With Discriminative Feature Grouping WACV 2021 Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger ACL 2021 HiGAN: Handwriting Imitation Conditioned on Arbitrary-Length Texts and Disentangled Styles AAAI 2021 Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs CVPR 2021 HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training With Crafted Input Noise ICCV 2021 House-GAN++: Generative Adversarial Layout Refinement Network towards Intelligent Computational Agent for Professional Architects CVPR 2021 How Does Data Augmentation Affect Privacy in Machine Learning? AAAI 2021 How Do We Move: Modeling Human Movement with System Dynamics AAAI 2021 How Robust Are Randomized Smoothing Based Defenses to Data Poisoning? CVPR 2021 How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness? NeurIPS 2021 How To Exploit the Transferability of Learned Image Compression to Conventional Codecs CVPR 2021 How Well Generative Adversarial Networks Learn Distributions JMLR 2021 IFDDS: An Anti-fraud Outbound Robot AAAI 2021 Improved Consistency Regularization for GANs AAAI 2021 Improved Corruption Robust Algorithms for Episodic Reinforcement Learning ICML 2021 Improved, Deterministic Smoothing for L_1 Certified Robustness ICML 2021 Improved OOD Generalization via Adversarial Training and Pretraing ICML 2021 Improving Adversarial Robustness via Channel-wise Activation Suppressing ICLR 2021