PolyLink: A Blockchain Based Decentralized Edge AI Platform for LLM Inference
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| 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 |