用区块链记录AI行为轨迹，实现风险可追溯、责任可追责。
AIAuditTrack: A Framework for AI Security system
- 基于区块链与可信身份，记录AI实体交互过程。
- 提出风险扩散算法，可追踪高危行为源头并预警。
- 适合需要审计与问责的复杂AI系统开发者。
大语言模型驱动的AI应用迅速发展，带来海量交互数据，引发安全、问责与风险溯源难题。本文提出AIAuditTrack（AAT）框架，基于区块链实现AI使用流量的可信记录与治理。AAT利用去中心化身份（DID）和可验证凭证（VC）建立可信可识别的AI实体，并将实体间交互轨迹上链，支持跨系统监督与审计。将AI实体建模为动态交互图中的节点，边表示特定时间的行为轨迹。基于此模型，提出风险扩散算法，用于追踪风险行为源头并跨实体传播预警。通过区块链吞吐量（TPS）指标评估系统性能，验证了在大规模交互记录下的可行性与稳定性。AAT为复杂多智能体环境中的AI审计、风险管理和责任归属提供了可扩展、可验证的解决方案。
原文摘要 · Abstract (English)
The rapid expansion of AI-driven applications powered by large language models has led to a surge in AI interaction data, raising urgent challenges in security, accountability, and risk traceability. This paper presents AiAuditTrack (AAT), a blockchain-based framework for AI usage traffic recording and governance. AAT leverages decentralized identity (DID) and verifiable credentials (VC) to establish trusted and identifiable AI entities, and records inter-entity interaction trajectories on-chain to enable cross-system supervision and auditing. AI entities are modeled as nodes in a dynamic interaction graph, where edges represent time-specific behavioral trajectories. Based on this model, a risk diffusion algorithm is proposed to trace the origin of risky behaviors and propagate early warnings across involved entities. System performance is evaluated using blockchain Transactions Per Second (TPS) metrics, demonstrating the feasibility and stability of AAT under large-scale interaction recording. AAT provides a scalable and verifiable solution for AI auditing, risk management, and responsibility attribution in complex multi-agent environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。