[论文解读] A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly

Yifan Yao, Jinhao Duan+4 more|arXiv (Cornell University)|Dec 4, 2023

Privacy-Preserving Technologies in Data参考文献 313被引用 44

一句话总结

对LLM安全与隐私工作的综合文献综述，将其分为三部分——积极的安全效益、潜在攻击路径，以及固有漏洞与防御。

ABSTRACT

Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized natural language understanding and generation. They possess deep language comprehension, human-like text generation capabilities, contextual awareness, and robust problem-solving skills, making them invaluable in various domains (e.g., search engines, customer support, translation). In the meantime, LLMs have also gained traction in the security community, revealing security vulnerabilities and showcasing their potential in security-related tasks. This paper explores the intersection of LLMs with security and privacy. Specifically, we investigate how LLMs positively impact security and privacy, potential risks and threats associated with their use, and inherent vulnerabilities within LLMs. Through a comprehensive literature review, the paper categorizes the papers into "The Good" (beneficial LLM applications), "The Bad" (offensive applications), and "The Ugly" (vulnerabilities of LLMs and their defenses). We have some interesting findings. For example, LLMs have proven to enhance code security (code vulnerability detection) and data privacy (data confidentiality protection), outperforming traditional methods. However, they can also be harnessed for various attacks (particularly user-level attacks) due to their human-like reasoning abilities. We have identified areas that require further research efforts. For example, Research on model and parameter extraction attacks is limited and often theoretical, hindered by LLM parameter scale and confidentiality. Safe instruction tuning, a recent development, requires more exploration. We hope that our work can shed light on the LLMs' potential to both bolster and jeopardize cybersecurity.

研究动机与目标

• 评估在各领域中LLMs对安全与隐私的积极影响。
• 识别在网络安全使用LLMs所产生的风险和威胁。
• 审查在训练和推理阶段LLMs的固有漏洞与防御。

提出的方法

• 对281篇关于LLM安全与隐私的论文进行全面的文献综述。
• 将论文分为好的一面（安全好处）、坏的一面（进攻性用途）和丑陋的一面（漏洞与防御）。
• 综合研究结果，以在各领域将基于LLM的方法与最先进的方法进行比较。

实验结果

研究问题

• RQ1 RQ1：在多样化领域中，LLMs如何为安全与隐私作出积极贡献？它们为安全社区带来了哪些优势？
• RQ2 RQ2：在网络安全中使用LLMs 会带来哪些潜在风险和威胁？
• RQ3 RQ3：LLMs内部存在哪些漏洞与弱点？以及如何防御这些威胁？

主要发现

• LLMs在安全性方面总体提升显著，尤其是在代码安全和数据安全/隐私方面，常常优于传统方法。
• 由于LLMs具有人类般的推理能力，用户级攻击最为普遍，带来安全与隐私风险。
• LLMs的漏洞分为AI模型固有和非AI固有两类，防御覆盖架构、训练和推理阶段。
• 在规模和保密性方面，安全指令微调和模型提取研究仍然有限且在很大程度上是理论性的。
• 本研究首次在一份统一综述中全面覆盖LLM安全与隐私的好、坏、丑三方面。