← Back to all news
arXiv AI By Yijia Fang, Yiqing Feng, Bingyu Li, Mingxun Zhou

KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing

Read the original on arXiv AI →

arXiv:2605. 29524v2 Announce Type: replace-cross Abstract: 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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Statistics ML
4d ago

Is Your LLM Relay Serving What It Claims? A low-cost and high-power test for LLM Relay Auditing

The paper introduces Distributional Fingerprint Auditing (DFA), a statistical method for auditing large language model (LLM) relay services. DFA uses only textual responses from suspect and trusted endpoints, repeatedly querying simple finite-choice probes to build categorical response distributions that serve as fingerprints. By comparing these fingerprints probe‑by‑probe and aggregating evidence with the Cauchy combination test, DFA produces an approximate endpoint‑level p‑value for audit decisions at a chosen significance level, and further supports model attribution and substitution ratio estimation through a likelihood‑based framework.

By Fangran Miao, Shengjie Niu, Jian Huang, Ting Li
llmsbenchmarks
More like this →
arXiv Computation and Language
Aug 28

An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic

The paper presents a simple detector for model extraction attacks on large language model APIs. It frames detection as a benign‑calibrated traffic‑window distribution test, embedding queries into a semantic space and using maximum mean discrepancy (MMD) to compare against historical benign traffic. Evaluated on fourteen attacker‑normal query pairs across four extraction scenarios, MMD achieves near‑perfect true‑positive rates while maintaining a 0.3% false‑positive rate, outperforming several existing baselines.

By Shuze Liu, Qianwen Guo, Yushun Dong
llms
More like this →
arXiv Machine Learning
Jul 14

One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions

arXiv:2607. 10252v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model advertised, and recent audits show that a substantial fraction of commercial endpoints deviate from the vendor's reference weights.

By Tomas Bruckner
llms
More like this →