Jun Feng

Privacy (1)

attention mechanism (2) adversarial learning (2) representation learning (1) adversarial robustness (1) few-shot learning (1) data poisoning (1) knowledge graph (1) backdoor attack (1) adversarial training (1) natural language understanding (1) deep learning (1) knowledge base (1) safety alignment (1) secure multi-party computation (1) graph embedding (1) direct preference optimization (1) differential privacy (1) adversarial perturbation (1) vision language model (1) federated learning (1)