IslandRun: Privacy-Aware Multi-Objective Orchestration for Distributed AI Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Malepati, Bala Siva Sai Akhil
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914174766940160
author Malepati, Bala Siva Sai Akhil
author_facet Malepati, Bala Siva Sai Akhil
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00595
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IslandRun: Privacy-Aware Multi-Objective Orchestration for Distributed AI Inference
Malepati, Bala Siva Sai Akhil
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Cryptography and Security
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.
title IslandRun: Privacy-Aware Multi-Objective Orchestration for Distributed AI Inference
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2512.00595