大语言模型会被愚弄吗？探究大语言模型中的脆弱性
Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
AI总结：
本文系统分析了大语言模型在模型、训练和推理阶段的脆弱性，并探讨了模型编辑与Chroma Teaming等缓解策略，为构建更安全稳健的LLM提出新方向。
摘要：
大语言模型（LLMs）的出现获得了显著的普及，并在自然语言处理（NLP）的各个领域中发挥了巨大作用。尽管它们的能力令人印象深刻，但识别并审视其脆弱性至关重要，尤其是当这些脆弱性可能带来代价高昂的后果时。例如，一个经过训练、用于对医疗文档进行简明摘要的LLM，在被暗中诱导时，可能会明确泄露患者的个人数据。这只是众多已被揭示的不幸案例之一，仍需要进一步研究来理解此类脆弱性背后的根本原因。在本研究中，我们深入探讨了多个脆弱性类别，包括基于模型的脆弱性、训练时脆弱性和推理时脆弱性，并讨论了缓解策略，其中包括旨在修改LLM行为的“模型编辑”（Model Editing），以及融合多种团队协作策略以增强LLM鲁棒性的“Chroma Teaming”。本文综合了每个脆弱性类别的研究发现，并提出了新的研究与发展方向。通过理解当前脆弱性的关键点，我们可以更好地预测和缓解未来风险，为更稳健、更安全的大语言模型铺平道路。
英文摘要：
The advent of Large Language Models (LLMs) has garnered significant popularity and wielded immense power across various domains within Natural Language Processing (NLP). While their capabilities are undeniably impressive, it is crucial to identify and scrutinize their vulnerabilities especially when those vulnerabilities can have costly consequences. One such LLM, trained to provide a concise summarization from medical documents could unequivocally leak personal patient data when prompted surreptitiously. This is just one of many unfortunate examples that have been unveiled and further research is necessary to comprehend the underlying reasons behind such vulnerabilities. In this study, we delve into multiple sections of vulnerabilities which are model-based, training-time, inference-time vulnerabilities, and discuss mitigation strategies including "Model Editing" which aims at modifying LLMs behavior, and "Chroma Teaming" which incorporates synergy of multiple teaming strategies to enhance LLMs' resilience. This paper will synthesize the findings from each vulnerability section and propose new directions of research and development. By understanding the focal points of current vulnerabilities, we can better anticipate and mitigate future risks, paving the road for more robust and secure 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。
