Jinyuan Jia

Privacy (4)

backdoor attack (7) adversarial robustness (5) certified robustness (4) adversarial learning (4) ensemble learning (3) data poisoning (3) jailbreak attack (3) federated learning (3) adversarial attack (3) randomized smoothing (2) model security (2) large language model (2) adversarial defense (2) adversarial perturbation (2) graph neural network (2) self-supervised learning (1) model robustness (1) game theory (1) contrastive learning (1) image synthesis (1)