Chunyi Zhou

backdoor attack (2) adversarial attack (2) vision-language model (2) adversarial learning (1) humor detection (1) adversarial training (1) model robustness (1) privacy budget (1) adversarial example (1) black-box attack (1) diffusion model (1) adversarial defense (1) pre-trained model (1) agent security (1) dataset distillation (1) machine learning security (1) transfer learning (1) adversarial transferability (1) benchmark evaluation (1) differential privacy (1)