| |||||||
ShanghaiTech University Knowledge Management System
LinkPrompt: Natural and Universal Adversarial Attacks on Prompt-based Language Models | |
2024-04-09 | |
状态 | 已发表 |
摘要 | Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks. Instead of using a fixed prompt template to fine-tune the model, some research demonstrates the effectiveness of searching for the prompt via optimization. Such prompt optimization process of prompt-based learning on PLMs also gives insight into generating adversarial prompts to mislead the model, raising concerns about the adversarial vulnerability of this paradigm. Recent studies have shown that universal adversarial triggers (UATs) can be generated to alter not only the predictions of the target PLMs but also the prediction of corresponding Prompt-based Fine-tuning Models (PFMs) under the prompt-based learning paradigm. However, UATs found in previous works are often unreadable tokens or characters and can be easily distinguished from natural texts with adaptive defenses. In this work, we consider the naturalness of the UATs and develop LinkPrompt, an adversarial attack algorithm to generate UATs by a gradient-based beam search algorithm that not only effectively attacks the target PLMs and PFMs but also maintains the naturalness among the trigger tokens. Extensive results demonstrate the effectiveness of LinkPrompt, as well as the transferability of UATs generated by LinkPrompt to open-sourced Large Language Model (LLM) Llama2 and API-accessed LLM GPT-3.5-turbo. |
DOI | arXiv:2403.16432 |
相关网址 | 查看原文 |
出处 | Arxiv |
WOS记录号 | PPRN:88275042 |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications |
文献类型 | 预印本 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/372920 |
专题 | 信息科学与技术学院 信息科学与技术学院_博士生 信息科学与技术学院_PI研究组_王雯婕组 |
通讯作者 | Wang, Wenjie |
作者单位 | ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China |
推荐引用方式 GB/T 7714 | Xu, Yue,Wang, Wenjie. LinkPrompt: Natural and Universal Adversarial Attacks on Prompt-based Language Models. 2024. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
个性服务 |
查看访问统计 |
谷歌学术 |
谷歌学术中相似的文章 |
[Xu, Yue]的文章 |
[Wang, Wenjie]的文章 |
百度学术 |
百度学术中相似的文章 |
[Xu, Yue]的文章 |
[Wang, Wenjie]的文章 |
必应学术 |
必应学术中相似的文章 |
[Xu, Yue]的文章 |
[Wang, Wenjie]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
修改评论
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。