KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
Relay and reseller APIs increasingly intermediate access to large language models (LLMs), but users have no direct way to verify that a claimed endpoint is actually serving the advertised model. We introduce KBF, a low-cost black-box auditing protocol that fingerprints model APIs using stable numerical recall near the knowledge boundary. Across 16 production LLM endpoints, KBF flags all 155 economically relevant substitutions without rejecting any same-model controls, remains stable under deployment variation, detects high-separation mixed-routing attacks when only 5-10% of traffic is substituted, and finds that 7 of 27 platform model cells in a six-platform shadow API audit are statistically inconsistent with their reference endpoints, with inconsistencies concentrated on premium Claude endpoints.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SoK: Large Language Model Copyright Auditing via Fingerprinting
The broad capabilities and substantial resources required to train Large Language Models (LLMs) make them valuable intellectual property, yet they remain vulnerable to copyright infringement, such as unauthorized use and…
SDBF: Steep-Decision-Boundary Fingerprinting for Hard-Label Tampering Detection of DNN Models
Cloud-based AI systems offer significant benefits but also introduce vulnerabilities, making deep neural network (DNN) models susceptible to malicious tampering. This tampering may involve harmful behavior injection …
SensitivityCALM: Curiosity-Driven Auditing for Large Language Models
Auditing Large Language Models (LLMs) is a crucial and challenging task. In this study, we focus on auditing black-box LLMs without access to their parameters, only to the provided service. We treat this type of auditing…
PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning
Machine unlearning for large language models (LLMs) aims to remove specified knowledge while preserving the rest of the model's capabilities. However, the boundary between knowledge to forget and knowledge to retain is o…
EditMF: Drawing an Invisible Fingerprint for Your Large Language Models
Training large language models (LLMs) is resource-intensive and expensive, making protecting intellectual property (IP) for LLMs crucial. Recently, embedding fingerprints into LLMs has emerged as a prevalent method for e…