Weimin Lyu

Privacy (1)

attention mechanism (2) model security (2) trojan attack (2) adversarial learning (2) natural language processing (1) text classification (1) semi-supervised learning (1) metaphor detection (1) adversarial machine learning (1) semantic parsing (1) sarcasm detection (1) bert model (1) mahalanobis distance (1) backdoor attack (1) role-playing agent (1) adversarial detection (1) adversarial attack (1) backdoor detection (1) self-supervised learning (1) adversarial robustness (1)