Skip to content

Encrypt What Matters: When Selective Homomorphic Inference Is Efficient

Sep 2026 · arXiv.org · Vol abs/2609.09357 · 0 citations · 16 references
Computer Science

Abstract

Fully homomorphic encryption (FHE) enables inference on private data without revealing it to the server, but evaluating an entire input under FHE is expensive. We study \emph{selective homomorphic inference}, where only a sensitive region of interest (ROI) is encrypted, and computations independent of that region are performed in plaintext. Selective evaluation produces the same output as full FHE on the same model, without retraining. Its efficiency depends on how quickly encrypted dependencies spread through the network. For small encrypted ROIs, locality-preserving architectures can achieve order-of-magnitude homomorphic-evaluation speedups, whereas architectures with early global mixing provide essentially no speedup. These results identify locality as the key architectural property governing the benefit of selective homomorphic inference.

View source

Similar papers

Preprint Oct 2026

Pacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service

This paper proposes Pacifo, a framework that adapts customized fine-tuning strategies to efficiently evaluate the ResNet20 model in the context of FHE, and introduces a public-private layer partitioning scheme and an efficient ReLU approximation, significantly reducing the number of private layers and costly FHE operat...

Yang-Zhuo Li, Gang He, Rui-Chen Zhang et al. · 0 citations
Preprint Oct 2026

GKS Fully Homomorphic Encryption: Security Analysis

All traditional encryption schemes share a fundamental operational vulnerability: encrypted data must be decrypted before it can be used. Fully homomorphic encryption eliminates this vulnerability by enabling computation directly on encrypted data, but existing FHE schemes impose substantial practical constraints that...

John R. Graham, Soundes Marzougui, Miloš Pavlović et al. · 0 citations
Book Open access Nov 2026

Private LLM Inference: Optimizing Tricycle

The adoption of Large Language Models (LLM) in scenarios with sensitive data requires the use of privacy-preserving technologies to guarantee confidentiality. Private LLM inference using Fully-Homomorphic Encryption (FHE) guarantees data privacy by encrypting the input beforehand and performing inference directly over...

Zaira Pindado, Hugo Sanz-González, Thomas Spendlhofer et al. · 0 citations

Coral: General and Efficient Framework for Homomorphic Evaluation of Symmetric Ciphers

This work presents C ORAL, a general and efficient transciphering framework built on TFHE that decomposes an entire decryption circuit to a uniform evaluation strategy and provides optimized procedures for four recurring computational modules: linear Boolean operations, sparse low-degree Boolean functions, modular addi...

Ji-Kang Bai, Rui-Da Wang, Xian-Hui Lu et al. · 0 citations
Open access 2026

ADAPTIVE SENSITIVE-LAYERS BASED HOMOMORPHIC ENCRYPTION FOR SCALABLE AND SECURE FEDERATED LEARNING

The findings suggest that selective homomorphic encryption provides a highly practical and scalable solution for privacy-preserving FL deployments in sensitive domains such as healthcare and medical imaging.

Mohammed El Amine Beyat, M. Benkaddour, Ahmed Korichi et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 3, 2026

Learn the rules: The hacker mindset

Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.