2025年2月3日
Proj CJI Paper Reading: Adversarial Demonstration Attacks on Large Language Models
摘要： Abstract 本文: Tools advICL Task: use demonstrations without changing the input to make LLM misclassify, the user input is known and fixed 特点：无法控制input， 阅读全文
posted @ 2025-02-03 02:42 雪溯 阅读(21) 评论(0) 推荐(0)