大型语言模型作为隐藏信息的载体
Large Language Models as Carriers of Hidden Messages
AI总结：
本文揭示了微调LLM嵌入隐藏文本易受解码过程分析提取的漏洞，提出了UTF提取攻击及UTFC防御范式，在保障模型性能的同时抵抗已知攻击。
摘要：
简单的微调可以将隐藏文本嵌入大型语言模型（LLMs）中，该文本仅在受到特定查询触发时才会显现。其应用包括LLM指纹识别（即嵌入唯一标识符以验证许可合规性）和隐写术（即LLM携带通过触发查询披露的隐藏信息）。我们的工作表明，尽管由于潜在触发器数量庞大，通过微调嵌入隐藏文本看似安全，但通过对LLM的输出解码过程进行分析，很容易将其提取出来。我们引入了一种名为Unconditional Token Forcing（UTF）的提取攻击方法，该方法通过迭代地将LLM词汇表中的词元输入模型，以揭示具有高词元概率的序列，从而识别隐藏文本候选。我们还提出了Unconditional Token Forcing Confusion（UTFC）防御范式，该范式能使隐藏文本抵抗所有已知的提取攻击，且与标准微调相比，不会降低LLM的通用性能。UTFC既有良性的应用（改进LLM指纹识别），也有恶意的应用（利用LLM创建隐蔽通信渠道）。
英文摘要：
Simple fine-tuning can embed hidden text into large language models (LLMs), which is revealed only when triggered by a specific query. Applications include LLM fingerprinting, where a unique identifier is embedded to verify licensing compliance, and steganography, where the LLM carries hidden messages disclosed through a trigger query. Our work demonstrates that embedding hidden text via fine-tuning, although seemingly secure due to the vast number of potential triggers, is vulnerable to extraction through analysis of the LLM's output decoding process. We introduce an extraction attack called Unconditional Token Forcing (UTF), which iteratively feeds tokens from the LLM's vocabulary to reveal sequences with high token probabilities, indicating hidden text candidates. We also present Unconditional Token Forcing Confusion (UTFC), a defense paradigm that makes hidden text resistant to all known extraction attacks without degrading the general performance of LLMs compared to standard fine-tuning. UTFC has both benign (improving LLM fingerprinting) and malign applications (using LLMs to create covert communication channels).
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。
