{"slug": "toploc-a-locality-sensitive-hashing-scheme-for-trustless-verifiable-inference", "title": "TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference", "summary": "Researchers proposed TOPLOC, a locality-sensitive hashing scheme for verifiable inference that detects unauthorized modifications to large language models with 100% accuracy and no false positives or negatives in empirical evaluations. The method reduces proof memory overhead by 1000x, requiring only 258 bytes per 32 tokens compared to 262 KB for Llama 3.1-8B-Instruct, enabling faster validation than original inference.", "body_md": "# Computer Science > Cryptography and Security\n\n  [Submitted on 27 Jan 2025 (\n\n[v1](https://arxiv.org/abs/2501.16007v1)), last revised 30 May 2025 (this version, v2)]\n# Title:TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference\n\n[View PDF](https://arxiv.org/pdf/2501.16007)\n\n[HTML (experimental)](https://arxiv.org/html/2501.16007v2)\n\nAbstract:Large language models (LLMs) have proven to be very capable, but access to frontier models currently relies on inference providers. This introduces trust challenges: how can we be sure that the provider is using the model configuration they claim? We propose TOPLOC, a novel method for verifiable inference that addresses this problem. TOPLOC leverages a compact locality-sensitive hashing mechanism for intermediate activations, which can detect unauthorized modifications to models, prompts, or precision with 100% accuracy, achieving no false positives or negatives in our empirical evaluations. Our approach is robust across diverse hardware configurations, GPU types, and algebraic reorderings, which allows for validation speeds significantly faster than the original inference. By introducing a polynomial encoding scheme, TOPLOC minimizes the memory overhead of the generated proofs by $1000\\times$, requiring only 258 bytes of storage per 32 new tokens, compared to the 262 KB requirement of storing the token embeddings directly for Llama 3.1-8B-Instruct. Our method empowers users to verify LLM inference computations efficiently, fostering greater trust and transparency in open ecosystems and laying a foundation for decentralized, verifiable and trustless AI services.\n    \n\n## Submission history\n\nFrom: Jack Min Ong Mr [\n[view email](https://arxiv.org/show-email/c0684d24/2501.16007)]\n\n**Mon, 27 Jan 2025 12:46:45 UTC (478 KB)**\n\n[\\[v1\\]](https://arxiv.org/abs/2501.16007v1)\n**[v2]** Fri, 30 May 2025 23:07:40 UTC (139 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/toploc-a-locality-sensitive-hashing-scheme-for-trustless-verifiable-inference", "canonical_source": "https://arxiv.org/abs/2501.16007", "published_at": "2026-08-31 09:00:00+00:00", "updated_at": "2026-09-07 21:30:54.158052+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-safety", "ai-research"], "entities": ["TOPLOC", "Llama 3.1-8B-Instruct"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/toploc-a-locality-sensitive-hashing-scheme-for-trustless-verifiable-inference", "markdown": "https://wpnews.pro/news/toploc-a-locality-sensitive-hashing-scheme-for-trustless-verifiable-inference.md", "text": "https://wpnews.pro/news/toploc-a-locality-sensitive-hashing-scheme-for-trustless-verifiable-inference.txt", "jsonld": "https://wpnews.pro/news/toploc-a-locality-sensitive-hashing-scheme-for-trustless-verifiable-inference.jsonld"}}