让分布式AI推理在隐私、性能和成本间自动平衡
IslandRun: Privacy-Aware Multi-Objective Orchestration for Distributed AI Inference
- 将设备、边缘和云视为独立岛屿，智能路由请求
- 支持跨信任边界的数据安全流转，隐私零泄露
- 适合注重隐私的医疗、金融等敏感领域应用
现代AI推理面临根本性矛盾：单一计算资源无法同时兼顾性能、隐私保护、成本控制与可信度。现有编排框架仅优化单一目标（如Kubernetes关注延迟，联邦学习保障隐私，边缘计算降低网络距离），在真实异构环境下表现不佳。本文提出IslandRun，一种多目标编排系统，将计算资源视为跨越个人设备、私有边缘服务器与公共云的自治‘岛屿’。核心洞察：(1) 请求级异构性要求策略约束下的多目标优化；(2) 数据本地性允许将计算导向数据而非反之；(3) 类型化占位符净化技术可在信任边界间保留语义。IslandRun引入基于代理的路由机制、分层岛屿组（差异化信任）及可逆匿名化，构建了一种面向异构个人计算生态的隐私感知、去中心化推理编排新范式。
原文摘要 · Abstract (English)
Modern AI inference faces an irreducible tension: no single computational resource simultaneously maximizes performance, preserves privacy, minimizes cost, and maintains trust. Existing orchestration frameworks optimize single dimensions (Kubernetes prioritizes latency, federated learning preserves privacy, edge computing reduces network distance), creating solutions that struggle under real-world heterogeneity. We present IslandRun, a multi-objective orchestration system that treats computational resources as autonomous "islands" spanning personal devices, private edge servers, and public cloud. Our key insights: (1) request-level heterogeneity demands policy-constrained multi-objective optimization, (2) data locality enables routing compute to data rather than data to compute, and (3) typed placeholder sanitization preserves context semantics across trust boundaries. IslandRun introduces agent-based routing, tiered island groups with differential trust, and reversible anonymization. This establishes a new paradigm for privacy-aware, decentralized inference orchestration across heterogeneous personal computing ecosystems.
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。