Truc Nguyen

Differential Privacy (2) Privacy (1)

membership inference attack (2) adversarial attack (2) differential privacy (2) federated learning (2) feature importance (1) backdoor attack (1) convolutional neural network (1) adversarial defense (1) mixture of expert (1) model explanation (1) privacy leakage (1) membership inference (1) local differential privacy (1) acoustic scene classification (1) large language model (1) mixup data augmentation (1) privacy attack (1) model security (1) explainable ai (1)