Juan Wen

model fingerprinting (2) adversarial learning (1) adversarial robustness (1) model security (1) domain generalization (1) text classification (1) backdoor defense (1) adversarial attack (1) intellectual property protection (1) ownership verification (1) ai-generated text detection (1) chain of thought (1) large language model (1) linguistic steganography (1) adversarial knowledge distillation (1) token filter attack (1) reinforcement learning (1) sentence verification attack (1)