Adversarial Learning

Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class NeurIPS 2022 Measuring CLEVRness: Black-box Testing of Visual Reasoning Models ICLR 2022 MINIMAL: Mining Models for Universal Adversarial Triggers AAAI 2022 MockingBERT: A Method for Retroactively Adding Resilience to NLP Models COLING 2022 Modeling Adversarial Noise for Adversarial Training ICML 2022 Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks NeurIPS 2022 Neurotoxin: Durable Backdoors in Federated Learning ICML 2022 NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models CVPR 2022 On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles CVPR 2022 One-shot Neural Backdoor Erasing via Adversarial Weight Masking NeurIPS 2022 On Improving Adversarial Transferability of Vision Transformers ICLR 2022 Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future IJCAI 2022 On Optimal Learning Under Targeted Data Poisoning NeurIPS 2022 On the power of adaptivity in statistical adversaries COLT 2022 PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks COLING 2022 Particle-based Adversarial Local Distribution Regularization AISTATS 2022 Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense ACL 2022 PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack COLING 2022 Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack CVPR 2022 Probing Script Knowledge from Pre-Trained Models EMNLP 2022 Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022 Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization ICML 2022 Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets NeurIPS 2022 Real-Time Neural Voice Camouflage ICLR 2022 Removing Batch Normalization Boosts Adversarial Training ICML 2022