PAL: Proxy-Guided Black-Box Attack on Large Language Models

Authors: Chawin Sitawarin, Norman Mu, David Wagner, Alexandre Araujo
Published: 2024-02-15

Source: https://arxiv.org/abs/2402.09674

PDF: https://arxiv.org/pdf/2402.09674

Labels Predicted by AI

プロンプトインジェクション 攻撃手法 LLMセキュリティ

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Large Language Models (LLMs) have surged in popularity in recent months, but they have demonstrated concerning capabilities to generate harmful content when manipulated. While techniques like safety fine-tuning aim to minimize harmful use, recent works have shown that LLMs remain vulnerable to attacks that elicit toxic responses. In this work, we introduce the Proxy-Guided Attack on LLMs (PAL), the first optimization-based attack on LLMs in a black-box query-only setting. In particular, it relies on a surrogate model to guide the optimization and a sophisticated loss designed for real-world LLM APIs. Our attack achieves 84 Llama-2-7B, compared to 4 GCG++, an improvement to the GCG attack that reaches 94 Llama-2-7B, and the Random-Search Attack on LLMs (RAL), a strong but simple baseline for query-based attacks. We believe the techniques proposed in this work will enable more comprehensive safety testing of LLMs and, in the long term, the development of better security guardrails. The code can be found at https://github.com/chawins/pal.