Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test

[2506.06975] Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Cryptography and Security arXiv:2506.06975 (cs) [Submitted on 8 Jun 2025 ( v1 ), last revised 9 Apr 2026 (this version, v5)] Title: Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test Authors: Xiaoyuan Zhu , Yaowen Ye , Tianyi Qiu , Hanlin Zhu , Sijun Tan , Ajraf Mannan , Jonathan Michala , Raluca Ada Popa , Willie Neiswanger View a PDF of the paper titled Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test, by Xiaoyuan Zhu and 8 other authors View PDF HTML (experimental) Abstract: As API access becomes a primary interface to large language models (LLMs), users often interact with black-box systems that offer little transparency into the deployed model. To reduce costs or maliciously alter model behaviors, API providers may discreetly serve quantized or fine-tuned variants, which can degrade performance and compromise safety. Detecting such substitutions is difficult, as users lack access to model weights and, in most cases, even output logits. To tackle this problem, we propose a rank-based uniformity test that can verify the behavioral equality of a black-box LLM to a locally deployed authentic model. Our method is accurate, query-efficient, and avoids detectable query patterns, making it robust to adversarial providers that reroute or mix responses upon the detection of testing attempts. We evaluate the approach across diverse threat scenarios, including quantization, harmful fine-tuning, jailbreak prompts, and full model substitution, showing that it consistently achieves superior statistical power over prior methods under constrained query budgets. Subjects: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2506.06975 [cs.CR] (or arXiv:2506.06975v5 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2506.06975 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Xiaoyuan Zhu [ view email ] [v1] Sun, 8 Jun 2025 03:00:31 UTC (396 KB) [v2] Tue, 10 Jun 2025 02:21:06 UTC (396 KB) [v3] Wed, 11 Jun 2025 03:04:10 UTC (397 KB) [v4] Wed, 18 Mar 2026 23:06:10 UTC (594 KB) [v5] Thu, 9 Apr 2026 03:34:55 UTC (594 KB) Full-text links: Access Paper: View a PDF of the paper titled Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test, by Xiaoyuan Zhu and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2025-06 Change to browse by: cs cs.AI cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Compared to What? A Human-Anchored Security Benchmark for LLM-Generated Infrastructure-as-Code#618510
• HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation#1128547
• Identity or Prompt Noise? A Calibrated Invariance Audit of LLM Code Generation#1037194
• Identity or Prompt Noise? A Calibrated Invariance Audit of LLM Code Generation#1028784
• Reveree: Diagnosing LLM Reverse-Engineering Agents#627607