AI RESEARCH
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
arXiv CS.LG
•
ArXi:2606.03330v1 Announce Type: new 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.