FLIPS：通过伪随机序列为LLMs进行实例指纹识别
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
AI总结：
提出FLIPS方法，利用生成的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）的识别准确率，解决了现有指纹识别技术无法区分同一LLM不同配置的问题，为AI监管提供了实例级指纹识别新范式。
摘要：
文献揭示，大型语言模型（LLM）的行为不仅受其原始权重影响，还受其实例级参数（如指令提示、采样配置或量化）影响。在一种配置下生成安全输出的模型，在另一种配置下可能产生有毒内容。然而，当前的LLM识别技术（如指纹识别）侧重于知识产权保护，其设计倾向于对这些实例级参数的变化具有鲁棒性。这对AI监管构成了关键挑战，因为合规评估针对的是实际部署的行为，而非模型来源。在本文中，我们引入了实例级指纹识别，这是一种面向监管的范式，用于区分同一LLM的不同配置。我们的方法FLIPS利用生成的二进制随机序列中的偏差，在237个模型实例上达到96%（闭集）和90%（开集，其中一些目标未知）的识别准确率，而改编的LLMmap基线仅为35%。这表明实例级指纹识别对于监管既必要又实际可行。代码见https://this URL。
英文摘要：
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.
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。
