Tianlong Xu

large language model (3) model fingerprinting (1) neural network security (1) question answering (1) educational technology (1) intellectual property (1) error detection (1) autonomous learning (1) deep neural network (1) decision boundary (1) adversarial example (1) neural network fingerprinting (1) adversarial trajectory (1) intellectual property protection (1) ownership verification (1) removal attack (1) chain-of-thought prompting (1) error analysis (1) math word problem (1) conformity bia (1)