Automatic and Universal Prompt Injection Attacks against Large Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Xiaogeng, Yu, Zhiyuan, Zhang, Yizhe, Zhang, Ning, Xiao, Chaowei
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909132018155520
author Liu, Xiaogeng
Yu, Zhiyuan
Zhang, Yizhe
Zhang, Ning
Xiao, Chaowei
author_facet Liu, Xiaogeng
Yu, Zhiyuan
Zhang, Yizhe
Zhang, Ning
Xiao, Chaowei
contents Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks manipulate LLM-integrated applications into producing responses aligned with the attacker's injected content, deviating from the user's actual requests. The substantial risks posed by these attacks underscore the need for a thorough understanding of the threats. Yet, research in this area faces challenges due to the lack of a unified goal for such attacks and their reliance on manually crafted prompts, complicating comprehensive assessments of prompt injection robustness. We introduce a unified framework for understanding the objectives of prompt injection attacks and present an automated gradient-based method for generating highly effective and universal prompt injection data, even in the face of defensive measures. With only five training samples (0.3% relative to the test data), our attack can achieve superior performance compared with baselines. Our findings emphasize the importance of gradient-based testing, which can avoid overestimation of robustness, especially for defense mechanisms.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automatic and Universal Prompt Injection Attacks against Large Language Models
Liu, Xiaogeng
Yu, Zhiyuan
Zhang, Yizhe
Zhang, Ning
Xiao, Chaowei
Artificial Intelligence
Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks manipulate LLM-integrated applications into producing responses aligned with the attacker's injected content, deviating from the user's actual requests. The substantial risks posed by these attacks underscore the need for a thorough understanding of the threats. Yet, research in this area faces challenges due to the lack of a unified goal for such attacks and their reliance on manually crafted prompts, complicating comprehensive assessments of prompt injection robustness. We introduce a unified framework for understanding the objectives of prompt injection attacks and present an automated gradient-based method for generating highly effective and universal prompt injection data, even in the face of defensive measures. With only five training samples (0.3% relative to the test data), our attack can achieve superior performance compared with baselines. Our findings emphasize the importance of gradient-based testing, which can avoid overestimation of robustness, especially for defense mechanisms.
title Automatic and Universal Prompt Injection Attacks against Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2403.04957