LLM token rank-frequency distributions converge to a shared Mandelbrot distribution across models and domains, enabling a microsecond-scale statistical primitive for provenance verification and black-box anomaly triage.
Your Large Language Models Are Leaving Fingerprints
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2verdicts
UNVERDICTED 2representative citing papers
AP-Test identifies deployed guardrails in LLMs via adversarial prompt testing and a match score metric, reporting perfect accuracy on four open-source guardrails.
citing papers explorer
-
The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive
LLM token rank-frequency distributions converge to a shared Mandelbrot distribution across models and domains, enabling a microsecond-scale statistical primitive for provenance verification and black-box anomaly triage.
-
Peering Behind the Shield: Guardrail Identification in Large Language Models
AP-Test identifies deployed guardrails in LLMs via adversarial prompt testing and a match score metric, reporting perfect accuracy on four open-source guardrails.