Aishan Liu

Privacy (3)

adversarial attack (4) backdoor attack (4) knowledge distillation (3) benchmark evaluation (3) large language model (3) object detection (2) jailbreak attack (2) adversarial training (2) few-shot learning (2) adversarial robustness (2) reinforcement learning (2) model security (2) trigger pattern (2) model compression (2) backdoor defense (2) adversarial learning (2) adversarial example (2) domain adaptation (1) domain generalization (1) metric learning (1)