arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.20649cs.AIcs.CR
收藏

AIAuditTrack:AI安全系统的框架

AIAuditTrack: A Framework for AI Security system

organization= Huazhong University of Science;organization= Lingnan University;organization= Centre for Artificial Intelligence;Robotics (CAIR) Hong Kong Institute of Science \& Innovation, Chinese Academy of Sciences;Tsinghua University;Fujian Jiangxia University

Zixun Luo, Yuhang Fan, Yufei Li, Youzhi Zhang, Hengyu Lin, Ziqi Wang

AI总结:

AIAuditTrack通过区块链技术实现AI交互轨迹记录与治理,提供可扩展的AI安全审计与责任追溯方案。

摘要:

随着大型语言模型驱动的应用快速扩展,AI交互数据激增,引发了安全、责任和风险追溯方面的紧迫挑战。本文提出了AIAuditTrack(AAT),一个基于区块链的AI使用流量记录和治理框架。AAT利用去中心化身份(DID)和可验证凭证(VC)建立可信且可识别的AI实体,并在链上记录实体间的交互轨迹,以实现跨系统的监督和审计。AI实体被建模为动态交互图中的节点,边代表时间特定的行为轨迹。基于此模型,提出了一种风险扩散算法,用于追溯风险行为的起源并在涉及实体间传播早期预警。系统性能通过区块链事务每秒(TPS)指标进行评估,证明了AAT在大规模交互记录下的可行性和稳定性。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且可验证的解决方案。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑