Tsung-Yi Ho

Robotics (1) Security & Privacy (1) Privacy (1)

adversarial attack (6) jailbreak attack (4) large language model (4) diffusion model (4) backdoor attack (3) generative model (3) adversarial example (3) adversarial defense (3) adversarial robustness (3) model robustness (2) object detection (2) policy learning (2) deep neural network (2) safety alignment (2) robustness evaluation (2) multimodal learning (1) model evaluation (1) model security (1) prompt engineering (1) multi-agent reinforcement learning (1)