PolyLink: A Blockchain Based Decentralized Edge AI Platform for LLM Inference

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Hongbo, Cao, Jiannong, Yang, Bo, Bai, Dongbin, Cao, Yinfeng, Shen, Xiaoming, Zhang, Yinan, Liang, Jinwen, Jiang, Shan, Zhang, Mingjin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911189258207232
author Liu, Hongbo
Cao, Jiannong
Yang, Bo
Bai, Dongbin
Cao, Yinfeng
Shen, Xiaoming
Zhang, Yinan
Liang, Jinwen
Jiang, Shan
Zhang, Mingjin
author_facet Liu, Hongbo
Cao, Jiannong
Yang, Bo
Bai, Dongbin
Cao, Yinfeng
Shen, Xiaoming
Zhang, Yinan
Liang, Jinwen
Jiang, Shan
Zhang, Mingjin
contents The rapid advancement of large language models (LLMs) in recent years has revolutionized the AI landscape. However, the deployment model and usage of LLM services remain highly centralized, creating significant trust issues and costs for end users and developers. To address these issues, we propose PolyLink, a blockchain-based decentralized AI platform that decentralizes LLM development and inference. Specifically, PolyLink introduces a decentralized crowdsourcing architecture that supports single-device and cross-device model deployment and inference across heterogeneous devices at the edge. Moreover, to ensure the inference integrity, we design the TIQE protocol, which combines a lightweight cross-encoder model and an LLM-as-a-Judge for a high-accuracy inference evaluation. Lastly, we integrate a comprehensive token-based incentive model with dynamic pricing and reward mechanisms for all participants. We have deployed PolyLink and conducted an extensive real-world evaluation through geo-distributed deployment across heterogeneous devices. Results indicate that the inference and verification latency is practical. Our security analysis demonstrates that the system is resistant to model degradation attacks and validator corruptions. PolyLink is now available at https://github.com/IMCL-PolyLink/PolyLink.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PolyLink: A Blockchain Based Decentralized Edge AI Platform for LLM Inference
Liu, Hongbo
Cao, Jiannong
Yang, Bo
Bai, Dongbin
Cao, Yinfeng
Shen, Xiaoming
Zhang, Yinan
Liang, Jinwen
Jiang, Shan
Zhang, Mingjin
Cryptography and Security
Distributed, Parallel, and Cluster Computing
The rapid advancement of large language models (LLMs) in recent years has revolutionized the AI landscape. However, the deployment model and usage of LLM services remain highly centralized, creating significant trust issues and costs for end users and developers. To address these issues, we propose PolyLink, a blockchain-based decentralized AI platform that decentralizes LLM development and inference. Specifically, PolyLink introduces a decentralized crowdsourcing architecture that supports single-device and cross-device model deployment and inference across heterogeneous devices at the edge. Moreover, to ensure the inference integrity, we design the TIQE protocol, which combines a lightweight cross-encoder model and an LLM-as-a-Judge for a high-accuracy inference evaluation. Lastly, we integrate a comprehensive token-based incentive model with dynamic pricing and reward mechanisms for all participants. We have deployed PolyLink and conducted an extensive real-world evaluation through geo-distributed deployment across heterogeneous devices. Results indicate that the inference and verification latency is practical. Our security analysis demonstrates that the system is resistant to model degradation attacks and validator corruptions. PolyLink is now available at https://github.com/IMCL-PolyLink/PolyLink.
title PolyLink: A Blockchain Based Decentralized Edge AI Platform for LLM Inference
topic Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2510.02395