让小模型在本地安全推理，不泄露用户隐私。
P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems
- 小模型通过技能提示自主拆解任务、屏蔽敏感信息并重写
- 比基线方法隐私保护下推理质量提升1.69到3.66倍
- 无需额外训练或检测器，适合移动端私密推理场景
云端-本地大模型推理系统有望利用云侧大模型的推理能力，同时保护用户设备上的敏感数据。所有发送至云端的请求必须排除个人身份信息（PII），以防止外部数据泄露。现有隐私保护方法依赖提示扰动、实体掩码或模型微调，但可能扭曲语义上下文或需额外训练。本文提出P2Skill，一种基于提示的技能蒸馏方法：本地小语言模型（SLM）通过遵循技能提示，自主完成分解、感知PII的路由、改写与重构。技能通过云端大模型对执行失败的迭代优化不断精炼，使本地SLM能泛化于未记忆的PII模式，因此无需隐私特定微调或学习的辅助检测器。在四个领域的基准测试中，P2Skill在隐私保护条件下推理质量分别达到基线的1.69倍和3.66倍。
原文摘要 · Abstract (English)
Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on personal devices. Cloud-bound requests must exclude personally identifiable information (PII) to prevent external data leakage. Existing privacy-preserving methods rely on prompt perturbation, entity masking, or model fine-tuning, but these approaches may distort contextual semantics or require additional training. This paper proposes P2Skill, a prompt-based skill distillation method in which a local small language model (SLM) autonomously performs decomposition, PII-aware routing, paraphrasing, and reconstruction by following the skill prompts. Skills are iteratively refined from execution failures by a cloud LLM, enabling the local SLM to generalize beyond memorized PII patterns, and therefore P2Skill requires no privacy-specific fine-tuning or learned auxiliary detectors. Evaluation on a four-domain benchmark shows that P2Skill achieves $1.69\times$ and $3.66\times$ higher privacy-preserved inference quality than previous baselines.
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。