Khoa D Doan

Privacy (1)

backdoor attack (4) federated learning (2) model security (1) model robustness (1) adversarial machine learning (1) distributed learning (1) part-of-speech tagging (1) machine unlearning (1) deep learning (1) adversarial attack (1) adversarial perturbation (1) text watermarking (1) poisoning attack (1) right to be forgotten (1) trigger generation (1) model poisoning (1) decentralized learning (1) data distillation (1) text quality (1) large language model (1)