Zhengwei Fang

adversarial attack (2) black-box optimization (1) ensemble learning (1) posterior distribution (1) black-box attack (1) asymptotic normality (1) multimodal large language model (1) jailbreak attack (1) adversarial prompt (1) prompt optimization (1) privacy leakage (1) trustworthiness benchmark (1) trustworthy ai (1) security vulnerabilities (1) large language model (1) trustworthiness evaluation (1) multimodal bia (1) trustworthy multimodal large language model (1) multimodal trustworthiness benchmark (1) multimodal jailbreaking (1)