Hongcheng Gao

text classification (3) adversarial attack (3) backdoor attack (2) diffusion model (2) adversarial defense (2) benchmark evaluation (2) model compression (2) large language model (2) knowledge distillation (1) zero-shot learning (1) contrastive learning (1) uncertainty quantification (1) natural language processing (1) knowledge editing (1) model security (1) catastrophic forgetting (1) model unlearning (1) machine-generated text detection (1) prompt-based learning (1) adversarial robustness (1)