Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Luo, Zixun, Fan, Yuhang, Li, Yufei, Zhang, Youzhi, Lin, Hengyu, Wang, Ziqi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.20649
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912786452316160
author Luo, Zixun
Fan, Yuhang
Li, Yufei
Zhang, Youzhi
Lin, Hengyu
Wang, Ziqi
author_facet Luo, Zixun
Fan, Yuhang
Li, Yufei
Zhang, Youzhi
Lin, Hengyu
Wang, Ziqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20649
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AIAuditTrack: A Framework for AI Security system
Luo, Zixun
Fan, Yuhang
Li, Yufei
Zhang, Youzhi
Lin, Hengyu
Wang, Ziqi
Artificial Intelligence
Cryptography and Security
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.
title AIAuditTrack: A Framework for AI Security system
topic Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2512.20649