Jinghui Chen

Privacy (1)

backdoor attack (6) adversarial attack (6) large language model (6) adversarial robustness (5) federated learning (5) adversarial training (4) adversarial perturbation (3) adversarial learning (3) multimodal learning (3) nonconvex optimization (3) model alignment (3) jailbreak attack (2) foundation model (2) few-shot learning (2) multimodal large language model (2) trigger pattern (2) stochastic gradient descent (2) ai safety (2) model security (2) gradient compression (2)