Adversarial Learning

MORA: Improving Ensemble Robustness Evaluation with Model Reweighing Attack NeurIPS 2022 MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples NeurIPS 2022 Multi-Level Attentive Adversarial Learning With Temporal Dilation for Unsupervised Video Domain Adaptation WACV 2022 Multimodal Adversarially Learned Inference with Factorized Discriminators AAAI 2022 Natural Black-Box Adversarial Examples against Deep Reinforcement Learning AAAI 2022 Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks NeurIPS 2022 Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization AISTATS 2022 Not All Poisons are Created Equal: Robust Training against Data Poisoning ICML 2022 One-shot Neural Backdoor Erasing via Adversarial Weight Masking NeurIPS 2022 Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future IJCAI 2022 On the Adversarial Robustness of Mixture of Experts NeurIPS 2022 On the Generalization Analysis of Adversarial Learning ICML 2022 On the Robustness of Offensive Language Classifiers ACL 2022 Open-Topic False Information Detection on Social Networks with Contrastive Adversarial Learning EMNLP 2022 Particle-based Adversarial Local Distribution Regularization AISTATS 2022 Pay attention to your loss : understanding misconceptions about Lipschitz neural networks NeurIPS 2022 Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense ACL 2022 Phase Transition from Clean Training to Adversarial Training NeurIPS 2022 PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack COLING 2022 Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks ICML 2022 Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task EMNLP 2022 Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models NeurIPS 2022 Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack CVPR 2022 Pre-activation Distributions Expose Backdoor Neurons NeurIPS 2022 Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation EMNLP 2022