谷歌浏览器插件
订阅小程序
在清言上使用
VIPCreated with Sketch.

PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails

Neal Mangaokar,Ashish Hooda,Jihye Choi, Shreyas Chandrashekaran,Kassem Fawaz,Somesh Jha,Atul Prakash

Annual Meeting of the Association for Computational Linguistics（2024）

引用 34|浏览46
关键词
Language Modeling,Topic Modeling
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要