ORIGINAL RESEARCH article
Front. Phys.
Sec. Social Physics
This article is part of the Research TopicSecurity, Governance, and Challenges of the New Generation of Cyber-Physical-Social Systems, Volume IIView all 21 articles
PriRS: An AI-Driven Framework for Privacy and Reliability in Cyber-Physical-Social Systems Data Sharing
Provisionally accepted
- Guangdong Power Grid Co Ltd, Guangzhou, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Cyber-Physical-Social Systems (CPSS) impose stringent requirements for data sharing security and regulatory compliance. However, existing solutions fail to bridge the gap between rigid smart contracts and flexible social regulations. The core research question is: how can we enforce complex, human-readable regulatory policies within rigid blockchain transactions without creating scalability bottlenecks? To address this, we propose PriRS, an AI-driven privacy and reliability framework. First, we utilize an LLM-based Compliance Oracle within a Trusted Execution Environment (TEE). This agent intelligently analyzes regulations to ensure strict compliance before data authorization. Second, we introduce a "Majority Voting Group Data Sharing" mechanism. By combining Shamir's Secret Sharing with Conditional Proxy Re-encryption, we move heavy coordination off-chain. This ensures fairness and significantly improves throughput. Experimental results on the Sepolia testnet demonstrate that PriRS reduces on-chain Gas consumption by 92.3% compared to state-of-the-art schemes. Furthermore, the AI-driven oracle achieves 96.0% accuracy and 98.0% precision on policy violation detection, while maintaining 100% deterministic consistency across repeated runs in the TEE.
Keywords: Agent-based control, Blockchain, cyber-physical-social systems (CPSS), data sharing, Privacy
Received: 11 Nov 2025; Accepted: 12 Feb 2026.
Copyright: © 2026 Yao, Zhang, Liang, Liu, Zhu and Zhou. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Xu Yao
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.