arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.12867cs.CLcs.SE
收藏

通过越狱对 ChatGPT 进行红队测试:偏见、鲁棒性、可靠性与毒性

Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity

CSIRO’s Data61(联邦科学与工业研究组织Data61);Monash University(莫纳什大学);Australian National University(澳大利亚国立大学)

Terry Yue Zhuo, Yujin Huang, Chunyang Chen, Zhenchang Xing

AI总结:

本文通过红队测试方法从偏见、可靠性、鲁棒性和毒性四个维度系统分析 ChatGPT 的伦理风险,发现现有基准无法覆盖大量风险,并通过案例研究揭示问题,为构建负责任的 LLM 提供设计启示。

摘要:

自然语言处理(NLP)领域的最新突破使得以开放式方式合成和理解连贯文本成为可能,从而将理论算法转化为实际应用。大语言模型(LLMs)已对报告摘要软件和文案撰写等业务产生了显著影响。然而,观察表明,LLMs 可能表现出社会偏见和毒性,从而带来因不负责任使用而产生的伦理和社会危险后果。因此,应当开发面向负责任 LLMs 的大规模基准。尽管若干实证研究揭示了先进 LLMs 中存在一些伦理难题,但对当前 LLM 使用中的风险和有害行为仍缺乏系统性考察和用户研究。为了进一步指导未来负责任地构建伦理 LLMs 的工作,我们对 OpenAI 的 ChatGPT(注:本文中 ChatGPT 指 12 月 15 日发布的版本)开展了一种名为“红队测试”的定性研究方法,以更好地理解近期 LLMs 中伦理危险的实际特征。我们从四个视角对 ChatGPT 进行全面分析:1)偏见 2)可靠性 3)鲁棒性 4)毒性。根据我们所阐述的观点,我们在多个样本数据集上对 ChatGPT 进行了实证基准测试。我们发现大量伦理风险无法通过现有基准加以解决,因此通过额外的案例研究加以说明。此外,我们考察了我们的发现对 AI 伦理和 ChatGPT 有害行为的影响,以及负责任 LLMs 的未来问题和实际设计考量。我们相信,我们的发现可能为未来确定和缓解 LLM 应用中机器所带来的伦理危害的工作提供启示。

英文摘要:

Recent breakthroughs in natural language processing (NLP) have permitted the synthesis and comprehension of coherent text in an open-ended way, therefore translating the theoretical algorithms into practical applications. The large language models (LLMs) have significantly impacted businesses such as report summarization software and copywriters. Observations indicate, however, that LLMs may exhibit social prejudice and toxicity, posing ethical and societal dangers of consequences resulting from irresponsibility. Large-scale benchmarks for accountable LLMs should consequently be developed. Although several empirical investigations reveal the existence of a few ethical difficulties in advanced LLMs, there is little systematic examination and user study of the risks and harmful behaviors of current LLM usage. To further educate future efforts on constructing ethical LLMs responsibly, we perform a qualitative research method called ``red teaming'' on OpenAI's ChatGPT\footnote{In this paper, ChatGPT refers to the version released on Dec 15th.} to better understand the practical features of ethical dangers in recent LLMs. We analyze ChatGPT comprehensively from four perspectives: 1) \textit{Bias} 2) \textit{Reliability} 3) \textit{Robustness} 4) \textit{Toxicity}. In accordance with our stated viewpoints, we empirically benchmark ChatGPT on multiple sample datasets. We find that a significant number of ethical risks cannot be addressed by existing benchmarks, and hence illustrate them via additional case studies. In addition, we examine the implications of our findings on AI ethics and harmal behaviors of ChatGPT, as well as future problems and practical design considerations for responsible LLMs. We believe that our findings may give light on future efforts to determine and mitigate the ethical hazards posed by machines in LLM applications.

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。

↑