Ren Pang

backdoor attack (2) adversarial robustness (1) few-shot learning (1) neural network security (1) self-supervised learning (1) model behavior (1) neural network interpretability (1) model analysis (1) deep neural network (1) adversarial defense (1) pre-trained language model (1) user interaction (1) query language (1) adversarial input (1) interactive framework (1) declarative query language (1) representation invariance (1) interactive explanation (1) representation learning (1) poisoning sample (1)