Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seo, Jungwon, Catak, Ferhat Ozgur, Rong, Chunming, Jang, Jaeyeon
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910039978016768
author Seo, Jungwon
Catak, Ferhat Ozgur
Rong, Chunming
Jang, Jaeyeon
author_facet Seo, Jungwon
Catak, Ferhat Ozgur
Rong, Chunming
Jang, Jaeyeon
contents Federated Inference (FI) studies how independently trained and privately owned models can collaborate at inference time without sharing data or model parameters. While recent work has explored secure and distributed inference from disparate perspectives, a unified abstraction and system-level understanding of FI remain lacking. This paper positions FI as a distinct collaborative paradigm, complementary to federated learning, and identifies two fundamental requirements that govern its feasibility: inference-time privacy preservation and meaningful performance gains through collaboration. We formalize FI as a protected collaborative computation, analyze its core design dimensions, and examine the structural trade-offs that arise when privacy constraints, non-IID data, and limited observability are jointly imposed at inference time. Through a concrete instantiation and empirical analysis, we highlight recurring friction points in privacy-preserving inference, ensemble-based collaboration, and incentive alignment. Our findings suggest that FI exhibits system-level behaviors that cannot be directly inherited from training-time federation or classical ensemble methods. Overall, this work provides a unifying perspective on FI and outlines open challenges that must be addressed to enable practical, scalable, and privacy-preserving collaborative inference systems.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02214
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving
Seo, Jungwon
Catak, Ferhat Ozgur
Rong, Chunming
Jang, Jaeyeon
Artificial Intelligence
Cryptography and Security
Machine Learning
Federated Inference (FI) studies how independently trained and privately owned models can collaborate at inference time without sharing data or model parameters. While recent work has explored secure and distributed inference from disparate perspectives, a unified abstraction and system-level understanding of FI remain lacking. This paper positions FI as a distinct collaborative paradigm, complementary to federated learning, and identifies two fundamental requirements that govern its feasibility: inference-time privacy preservation and meaningful performance gains through collaboration. We formalize FI as a protected collaborative computation, analyze its core design dimensions, and examine the structural trade-offs that arise when privacy constraints, non-IID data, and limited observability are jointly imposed at inference time. Through a concrete instantiation and empirical analysis, we highlight recurring friction points in privacy-preserving inference, ensemble-based collaboration, and incentive alignment. Our findings suggest that FI exhibits system-level behaviors that cannot be directly inherited from training-time federation or classical ensemble methods. Overall, this work provides a unifying perspective on FI and outlines open challenges that must be addressed to enable practical, scalable, and privacy-preserving collaborative inference systems.
title Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving
topic Artificial Intelligence
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2603.02214