Luyao Niu

large language model (6) safety alignment (3) adversarial learning (3) jailbreak attack (3) knowledge distillation (2) chain-of-thought reasoning (2) decoding strategy (2) adversarial attack (2) llm safety (2) instruction tuning (2) backdoor attack (2) gaussian process (1) harmful content (1) model safety (1) model robustness (1) safety evaluation (1) adversarial training (1) social network (1) adversarial prompt (1) text generation (1)