Kaike Zhang

model security (1) neural network security (1) adversarial training (1) instruction following (1) poisoning attack (1) evaluation benchmark (1) recommender system (1) pretrained language model (1) backdoor mitigation (1) backdoor attack detection (1) large language model (1) textual backdoor attack (1) poison detection (1) lexical instruction (1) programmatic evaluation (1) adversarial collaborative filtering (1)