Adversarial Learning

IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking CVPR 2021 Joint Generative and Contrastive Learning for Unsupervised Person Re-Identification CVPR 2021 Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction EMNLP 2021 Knowledge-Enriched Distributional Model Inversion Attacks ICCV 2021 KnowMAN: Weakly Supervised Multinomial Adversarial Networks EMNLP 2021 LAFEAT: Piercing Through Adversarial Defenses With Latent Features CVPR 2021 Large Norms of CNN Layers Do Not Hurt Adversarial Robustness AAAI 2021 Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training ACL 2021 Learning from the Best: Rationalizing Predictions by Adversarial Information Calibration AAAI 2021 Learning Semantic Context from Normal Samples for Unsupervised Anomaly Detection AAAI 2021 Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided Meta-Learning AAAI 2021 Learning to Generate Noise for Multi-Attack Robustness ICML 2021 Learning Transferable Adversarial Perturbations NeurIPS 2021 LiBRe: A Practical Bayesian Approach to Adversarial Detection CVPR 2021 Linear Semantics in Generative Adversarial Networks CVPR 2021 Local Aggressive Adversarial Attacks on 3D Point Cloud ACML 2021 Local Convergence Analysis of Gradient Descent Ascent with Finite Timescale Separation ICLR 2021 LocalGAN: Modeling Local Distributions for Adversarial Response Generation JMLR 2021 Low Curvature Activations Reduce Overfitting in Adversarial Training ICCV 2021 Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries ICML 2021 Manipulating SGD with Data Ordering Attacks NeurIPS 2021 MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation ACL 2021 MaxUp: Lightweight Adversarial Training With Data Augmentation Improves Neural Network Training CVPR 2021 MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation CVPR 2021 Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer EMNLP 2021