关注
Zichu Wu
Zichu Wu
未知所在单位机构
在 uwaterloo.ca 的电子邮件经过验证
标题
引用次数
引用次数
年份
Shadowcast: Stealthy data poisoning attacks against vision-language models
Y Xu, J Yao, M Shu, Y Sun, Z Wu, N Yu, T Goldstein, F Huang
arXiv preprint arXiv:2402.06659, 2024
152024
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
M Ding, C Deng, J Choo, Z Wu, A Agrawal, A Schwarzschild, T Zhou, ...
arXiv preprint arXiv:2409.18433, 2024
2024
Model Manipulation Attacks Enable More Rigorous Evaluations of LLM Capabilities
Z Che, S Casper, A Satheesh, R Gandikota, D Rosati, S Slocum, ...
Neurips Safe Generative AI Workshop 2024, 0
系统目前无法执行此操作，请稍后再试。
文章 1–3