面向边缘分布式生成AI推理的可信路由
Trust-Aware Routing for Distributed Generative AI Inference at the Edge
AI总结：
本文提出G-TRAC框架，通过算法路径选择与协议设计结合，解决边缘设备间生成AI推理的可靠性与信任问题，提升推理完成率并隔离不可靠节点。
摘要：
随着生成AI的部署，推理任务越来越多地在去中心化和异构边缘设备上执行，而非单一可信服务器。在这样的环境中，单个设备故障或不当行为可能破坏整个推理过程，使传统尽力而为的点对点路由不足。为此，本文提出G-TRAC框架，整合算法路径选择与系统级协议设计，确保稳健的分布式推理。首先，将路由问题建模为风险受限最短路径计算，并引入多项式时间解决方案，结合信任地板修剪与Dijkstra搜索，实现亚毫秒级中位路由延迟，并在更大规模下保持低于10毫秒。其次，为支持动态环境中的路由逻辑，框架采用混合信任架构，在稳定锚点维护全局声誉状态，同时通过后台同步向边缘节点传播轻量级更新。实验评估表明，G-TRAC显著提高了推理完成率，有效隔离不可靠节点，并在节点故障和网络分区下保持稳健执行。
英文摘要：
Emerging deployments of Generative AI increasingly execute inference across decentralized and heterogeneous edge devices rather than on a single trusted server. In such environments, a single device failure or misbehavior can disrupt the entire inference process, making traditional best-effort peer-to-peer routing insufficient. Coordinating distributed generative inference therefore requires mechanisms that explicitly account for reliability, performance variability, and trust among participating peers. In this paper, we present G-TRAC, a trust-aware coordination framework that integrates algorithmic path selection with system-level protocol design to ensure robust distributed inference. First, we formulate the routing problem as a \textit{Risk-Bounded Shortest Path} computation and introduce a polynomial-time solution that combines trust-floor pruning with Dijkstra's search, achieving sub-millisecond median routing latency at practical edge scales, and remaining below 10 ms at larger scales. Second, to operationally support the routing logic in dynamic environments, the framework employs a \textit{Hybrid Trust Architecture} that maintains global reputation state at stable anchors while disseminating lightweight updates to edge peers via background synchronization. Experimental evaluation on a heterogeneous testbed of commodity devices demonstrates that G-TRAC significantly improves inference completion rates, effectively isolates unreliable peers, and sustains robust execution even under node failures and network partitions.
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。
