Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding

2026-08-29

AI Summary

本文针对云边协同解码中的隐私泄露问题，通过构建评估框架分析风险，并提出CoVeil机制优化传输信号以减少泄露同时保持协作质量。

Abstract

Applications such as personalized assistance and proprietary document analysis require large language models (LLMs) to generate outputs from private data. Yet powerful LLMs typically cannot be deployed on the resource-constrained devices where private data resides, and uploading private data to cloud-hosted LLMs exposes sensitive information. Recent work addresses this tension with a cloud-edge collaborative decoding paradigm, where private data are kept on the edge with a small language model (SLM) producing next-token distributions, which are fused with predictions from a cloud LLM operating solely on public data. In this paper, we systematically analyze the privacy risks of such a paradigm with a novel evaluation framework using constructed QA datasets, which show that such collaboration can expose substantial private-context information. To address such privacy leakage, we propose CoVeil, a defense mechanism which dynamically optimizes transmitted signals to suppress leakage during decoding time while preserving the collaborative quality. Extensive evaluations demonstrate that CoVeil consistently improves the privacy-utility trade-off over existing baselines by reducing data leakage by up to 87.2%, with minimal accuracy loss.

Problem

• privacy leakage
• cloud-edge collaborative decoding
• private data

Innovation

• cloud-edge collaborative decoding
• privacy leakage
• dynamic optimization
• CoVeil