PANDORA: Jailbreak GPTs by Retrieval Augmented Generation Poisoning
2024-2-9 09:30:42 Author: www.ndss-symposium.org(查看原文) 阅读量:7 收藏

Gelei Deng, Yi Liu (Nanyang Technological University), Yuekang Li (The University of New South Wales), Wang Kailong(Huazhong University of Science and Technology), Tianwei Zhang, Yang Liu (Nanyang Technological University)

Large Language Models (LLMs) have gained immense popularity and are being increasingly applied in various domains. Consequently, ensuring the security of these models is of paramount importance. Jailbreak attacks, which manipulate LLMs to generate malicious content, are recognized as a significant vulnerability. While existing research has predominantly focused on direct jailbreak attacks on LLMs, there has been limited exploration of indirect methods. The integration of various plugins into LLMs, notably Retrieval Augmented Generation (RAG), which enables LLMs to incorporate external knowledge bases into their response generation such as GPTs, introduces new avenues for indirect jailbreak attacks.

To fill this gap, we investigate indirect jailbreak attacks on LLMs, particularly GPTs, introducing a novel attack vector named Retrieval Augmented Generation Poisoning. This method, PANDORA, exploits the synergy between LLMs and RAG through prompt manipulation to generate unexpected responses. PANDORA uses maliciously crafted content to influence the RAG process, effectively initiating jailbreak attacks. Our preliminary tests show that PANDORA successfully conducts jailbreak attacks in four different scenarios, achieving higher success rates than direct attacks, with 64.3% for GPT-3.5 and 34.8% for GPT-4.

View More Papers

WIP: Delegation Related Privacy Issues in Matter

Ze Jin, Yiwei Fang, Haoqiang Wang, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Indiana University Bloomington, Kexin Chen, Qixu Liu, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Luyi Xing, Indiana University Bloomington

Read More


文章来源: https://www.ndss-symposium.org/ndss-paper/auto-draft-541/
如有侵权请联系:admin#unsafe.sh