arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.14644cs.CL
收藏

基于情境上下文的大语言模型人类可解释对抗性提示攻击

Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context

Booz Allen Hamilton(博思艾伦汉密尔顿公司)

Nilanjana Das, Edward Raff, Manas Gaur

AI总结:

本研究提出一种情境驱动的上下文重写方法,将无意义的对抗性后缀转换为人类可理解的恶意提示,无需梯度即可在开源和专有大语言模型上实施攻击,且仅需1次尝试即可成功并在模型间转移。

摘要:

以往关于使用对抗性攻击测试大型语言模型(LLMs)漏洞的研究主要集中在无意义的提示注入上,这些注入在人工或自动化审查(例如通过字节熵)时很容易被检测到。然而,对于通过对抗性注入增强的无害且人类可理解的恶意提示的探索仍然有限。在本研究中,我们探索通过情境驱动的上下文重写,将无意义的后缀攻击转换为合理的提示。这使我们能够在没有任何梯度的情况下展示后缀转换,仅使用LLMs来执行攻击,从而更好地理解可能风险的范围。我们将独立的、有意义的对抗性插入与从电影中提取的情境相结合,以检查这是否可以欺骗LLM。这些情境从IMDB数据集中提取,提示遵循少样本思维链提示进行定义。我们的方法表明,成功的情境驱动攻击可以在开源和专有LLMs上执行。我们发现,在许多LLMs中,仅需1次尝试就能产生攻击,并且这些攻击可以在LLMs之间转移。

英文摘要:

Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte entropy). However, the exploration of innocuous human-understandable malicious prompts augmented with adversarial injections remains limited. In this research, we explore converting a nonsensical suffix attack into a sensible prompt via a situation-driven contextual re-writing. This allows us to show suffix conversion without any gradients, using only LLMs to perform the attacks, and thus better understand the scope of possible risks. We combine an independent, meaningful adversarial insertion and situations derived from movies to check if this can trick an LLM. The situations are extracted from the IMDB dataset, and prompts are defined following a few-shot chain-of-thought prompting. Our approach demonstrates that a successful situation-driven attack can be executed on both open-source and proprietary LLMs. We find that across many LLMs, as few as 1 attempt produces an attack and that these attacks transfer between LLMs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑