为本地大模型设计可验证的隐私保护框架，实现边端可控的私密推理。
AVEC: Bootstrapping Privacy for Local LLMs
- 基于敏感度与置信度动态分配差分隐私参数，实现自适应隐私控制。
- 通过设备端完整性校验和里程表会计机制，提供可验证的隐私保障。
- 提出理论极限与不可能结果，为后续实证研究指明方向。
本文提出 AVEC（自适应可验证边缘控制）框架，通过在边缘端强制执行隐私保护并支持委托查询的可验证性，实现本地语言模型的隐私启动。AVEC引入一种自适应预算算法，根据查询敏感度、本地置信度和历史使用情况动态分配差分隐私参数，并采用设备端可验证转换与完整性检查。我们基于里程表会计的Rényi差分隐私形式化了隐私保证，推导出效用上限、委托泄露边界，并证明确定性门控与仅哈希认证的不可行性。评估为仿真驱动，旨在分析机制行为与会计逻辑；不声称对实际大模型部署或任务性能的适用性。贡献在于构建概念架构与理论基础，为私有化本地大模型的实证研究开辟路径。
原文摘要 · Abstract (English)
This position paper presents AVEC (Adaptive Verifiable Edge Control), a framework for bootstrapping privacy for local language models by enforcing privacy at the edge with explicit verifiability for delegated queries. AVEC introduces an adaptive budgeting algorithm that allocates per-query differential privacy parameters based on sensitivity, local confidence, and historical usage, and uses verifiable transformation with on-device integrity checks. We formalize guarantees using Rényi differential privacy with odometer-based accounting, and establish utility ceilings, delegation-leakage bounds, and impossibility results for deterministic gating and hash-only certification. Our evaluation is simulation-based by design to study mechanism behavior and accounting; we do not claim deployment readiness or task-level utility with live LLMs. The contribution is a conceptual architecture and theoretical foundation that chart a pathway for empirical follow-up on privately bootstrapping local LLMs.
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。