缓解大型语言模型后门威胁：进展与挑战
Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges
AI总结：
本文系统综述了大型语言模型在开发与推理阶段面临的后门攻击威胁，梳理了防御与检测策略的最新进展，并指出了未来研究的关键挑战与方向。
摘要：
大型语言模型（LLMs）的进步已显著影响多个领域，包括网络搜索、医疗保健和软件开发。然而，随着这些模型规模扩大，它们变得更容易受到网络安全风险的影响，尤其是后门攻击。通过利用LLMs强大的记忆能力，攻击者可以通过操纵一小部分训练数据轻易地向LLMs注入后门，从而在下游应用中一旦隐藏后门被预定义触发器激活，就导致恶意行为。此外，指令调优和基于人类反馈的强化学习（RLHF）等新兴学习范式加剧了这些风险，因为它们严重依赖众包数据和人类反馈，而这些数据和反馈并未被完全控制。在本文中，我们对LLMs在开发或推理过程中出现的新兴后门威胁进行了全面综述，并涵盖了用于缓解LLMs后门威胁的防御与检测策略的最新进展。我们还概述了应对这些威胁的关键挑战，并指出了未来研究的重点领域。
英文摘要：
The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks, particularly backdoor attacks. By exploiting the potent memorization capacity of LLMs, adversaries can easily inject backdoors into LLMs by manipulating a small portion of training data, leading to malicious behaviors in downstream applications whenever the hidden backdoor is activated by the pre-defined triggers. Moreover, emerging learning paradigms like instruction tuning and reinforcement learning from human feedback (RLHF) exacerbate these risks as they rely heavily on crowdsourced data and human feedback, which are not fully controlled. In this paper, we present a comprehensive survey of emerging backdoor threats to LLMs that appear during LLM development or inference, and cover recent advancement in both defense and detection strategies for mitigating backdoor threats to LLMs. We also outline key challenges in addressing these threats, highlighting areas for future research.
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。
