mlsanityData to 7 Oct 2026

P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems

arXiv 2608.14094 ↗First posted 14 Aug 2026cs.CR cs.AIcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

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× and 3.66× higher privacy-preserved inference quality than previous baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 30 of its 44 references that are in the map. First posted on arXiv 14 Aug 2026.

Builds on

30 of 44 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  9. 2024GPT-4o System Cardcited by 4,467
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  11. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  12. 2020Extracting Training Data from Large Language Modelscited by 2,144
18 more
  1. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  2. 2023BloombergGPT: A Large Language Model for Financecited by 923
  3. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  4. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  5. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 278
  6. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
  7. 2023ProPILE: Probing Privacy Leakage in Large Language Modelscited by 127
  8. 2021Selective Differential Privacy for Language Modelingcited by 61
  9. 2024PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensemblescited by 54
  10. 2023Split-and-Denoise: Protect large language model inference with local differential privacycited by 30
  11. 2024PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restorationcited by 27
  12. 2024CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaborationcited by 25
  13. 2019Context-Aware Local Differential Privacycited by 18
  14. 2024Can Models Learn Skill Composition from Examples?cited by 17
  15. 2025Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challengescited by 14
  16. 2025PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaborationcited by 10
  17. 2024EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMscited by 9
  18. 2024Robust Utility-Preserving Text Anonymization Based on Large Language Modelscited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Redactor: An Empirical Evaluation of Eight Techniques for Privacy-Preserving LLM Requests
  2. 2026LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication
  3. 2026Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs
  4. 2026OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents
  5. 2025Towards Confidential and Efficient LLM Inference with Dual Privacy Protection
  6. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
  7. 2025A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness
  8. 2026Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs