通过伪随机序列识别大模型不同配置，助力合规监管
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
- 利用生成二进制序列的偏差实现实例指纹
- 闭集与开集识别准确率分别达96%和90%
- 适合监管机构评估模型实际部署行为
研究表明，大语言模型的行为不仅由原始权重决定，还受实例级参数影响，如指令提示、采样配置或量化方式。同一模型在不同配置下可能从生成安全内容变为产生有害内容。然而，现有大模型识别技术（如指纹）侧重知识产权保护，设计上强调对这些实例级参数变化的鲁棒性，难以满足监管中针对实际部署行为的合规评估需求。本文提出面向监管的实例级指纹方法FLIPS，利用生成二进制随机序列中的偏差，在237个模型实例上实现96%（闭集）和90%（开集，部分目标未知）的识别准确率，显著优于适应后的LLMmap基线（35%）。结果表明，实例级指纹既必要又可行。代码见https://github.com/GurvanR/FLIPS-LLM-Instance-Fingerprinting。
原文摘要 · Abstract (English)
Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters, such as instructional prompt, sampling configuration or quantization. A model that generates safe outputs under one configuration may produce toxic content under another. However, current LLM identification techniques (such as fingerprinting) focus on intellectual property protection, and their design favors robustness to changes in these instance-level parameters. This poses a critical challenge for AI regulation in which compliance assessments target actual deployed behaviors, not model provenance. In this paper, we introduce instance-level fingerprinting, a regulator-oriented paradigm that distinguishes configurations of the same LLM. Our method FLIPS, exploits biases in generated binary random sequences to reach 96% (closed-set) and 90% (open-set, where some targets are unknown) identification accuracy across 237 model instances, versus 35% for the adapted LLMmap baseline. This shows that instance-level fingerprinting is both necessary for regulation and practically feasible. Code available at https://github.com/GurvanR/FLIPS-LLM-Instance-Fingerprinting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。