AIAuditTrack: A Framework for AI Security system
Zixun Luo, Yuhang Fan, Yufei Li, Youzhi Zhang, Hengyu Lin, Ziqi Wang
TL;DR
AiAuditTrack (AAT) provides a blockchain-based framework for auditing AI interactions by binding AI entities with DID/VC identities, recording trajectory-based interaction graphs on-chain, and applying a diffusion-based risk propagation mechanism to trace responsibility and contain incidents. The system combines an on-chain Move-based layer with off-chain analysis and audit interfaces to enable real-time traceability, verification, and governance across multi-agent AI ecosystems. Experimental results demonstrate robust identity trustworthiness verification, full reconstruction of complex interaction paths, and effective defense against common security attacks, with TPS analyses supporting scalability. The work outlines concrete directions for performance optimization, cross-chain data integration, and advanced anomaly detection to reinforce security and accountability in AI-enabled ecosystems.
Abstract
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.