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

• URL: http://arxiv.org/abs/2608.14094v1
• Date: Fri, 14 Aug 2026 08:56:11 GMT
• Title: P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems
• Abstract summary: Cloud-bound requests must exclude personally identifiable information (PII) to prevent external data leakage.<n>Existing privacy-preserving methods rely on prompt perturbation, entity masking, or model fine-tuning.<n>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.
• Score: 0.5252190504926357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs [61.15237978606501]
  Large language models can infer private user attributes from user-generated text.<n>Existing anonymization-based defenses are coarse-grained, lacking word-level precision in anonymizing privacy-leaking elements.<n>We propose a unified defense framework that combines fine-grained anonymization (TRACE) with inference-preventing optimization (RPS)
  arXiv  Detail & Related papers  (2026-02-12T03:37:50Z)
• Unintended Memorization of Sensitive Information in Fine-Tuned Language Models [24.228889351240838]
  Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII)<n>We design controlled extraction probes to quantify unintended PII memorization and study how factors such as language, PII frequency, task type, and model size influence memorization behavior.
  arXiv  Detail & Related papers  (2026-01-24T15:08:45Z)
• Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning [27.452191507918148]
  Large language models (LLMs) exhibit powerful capabilities but risk memorizing sensitive personally identifiable information (PII) from their training data.<n>We propose Data-Free Selective Unlearning (DFSU), a novel privacy-preserving framework that removes sensitive PII from an LLM without requiring its training data.<n>Our approach first synthesizes pseudo-PII through language model inversion, then constructs token-level privacy masks for these synthetic samples, and finally performs token-level selective unlearning.
  arXiv  Detail & Related papers  (2026-01-22T02:43:12Z)
• PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration [8.776463501718737]
  We propose a context-aware framework that dynamically balances privacy and inference quality.<n>PRISM executes in four stages: (1) the edge device profiles entity-level sensitivity; (2) a soft gating module on the edge selects an execution mode - cloud, edge, or collaboration; (3) for collaborative paths, the edge applies adaptive two-layer local differential privacy based on entity risks; and (4) the cloud LLM generates a semantic sketch from the perturbed prompt.
  arXiv  Detail & Related papers  (2025-11-27T22:32:33Z)
• The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization [53.51921540246166]
  We show that Language Large Models (LLMs) can exploit the contextual vulnerability of DP-sanitized texts.<n>Experiments uncover a double-edged sword effect of LLM reconstructions on privacy and utility.<n>We propose recommendations for using data reconstruction as a post-processing step.
  arXiv  Detail & Related papers  (2025-08-26T12:22:45Z)
• DP-Fusion: Token-Level Differentially Private Inference for Large Language Models [51.71591819896191]
  Large language models (LLMs) do not preserve privacy at inference-time.<n> DP-Fusion provably bounds the influence a set of tokens in the context can have on the LLM's output.<n>We show that our method creates token-level provably privatized documents with substantially improved theoretical and empirical privacy.
  arXiv  Detail & Related papers  (2025-07-06T20:49:39Z)
• PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders [8.483679748399037]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but pose privacy risks by memorizing and leaking Personally Identifiable Information (PII)<n>Existing mitigation strategies, such as differential privacy and neuron-level interventions, often degrade model utility or fail to effectively prevent leakage.<n>We introduce PrivacyScalpel, a novel privacy-preserving framework that leverages interpretability techniques to identify and mitigate PII leakage while maintaining performance.
  arXiv  Detail & Related papers  (2025-03-14T09:31:01Z)
• ConfusionPrompt: Practical Private Inference for Online Large Language Models [3.8134804426693094]
  State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. We introduce ConfusionPrompt, a novel framework for private LLM inference that protects user privacy by decomposing the original prompt into smaller sub-prompts. We show that ConfusionPrompt achieves significantly higher utility than local inference methods using open-source models and perturbation-based techniques.
  arXiv  Detail & Related papers  (2023-12-30T01:26:42Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• Privacy Side Channels in Machine Learning Systems [87.53240071195168]
  We introduce privacy side channels: attacks that exploit system-level components to extract private information. For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees. We further show that systems which block language models from regenerating training data can be exploited to exfiltrate private keys contained in the training set.
  arXiv  Detail & Related papers  (2023-09-11T16:49:05Z)
• Analyzing Leakage of Personally Identifiable Information in Language Models [13.467340359030855]
  Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Scrubbing techniques reduce but do not prevent the risk of PII leakage. It is unclear to which extent algorithmic defenses such as differential privacy, designed to guarantee user-level privacy, prevent PII disclosure.
  arXiv  Detail & Related papers  (2023-02-01T16:04:48Z)
• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [69.66654761324702]
  We propose a simple yet effective just-fine-tune-twice privacy mechanism to achieve SDP for large Transformer-based language models. Experiments show that our models achieve strong performance while staying robust to the canary insertion attack.
  arXiv  Detail & Related papers  (2022-04-15T22:36:55Z)
• AdaPrompt: Adaptive Model Training for Prompt-based NLP [77.12071707955889]
  We propose AdaPrompt, adaptively retrieving external data for continual pretraining of PLMs. Experimental results on five NLP benchmarks show that AdaPrompt can improve over standard PLMs in few-shot settings. In zero-shot settings, our method outperforms standard prompt-based methods by up to 26.35% relative error reduction.
  arXiv  Detail & Related papers  (2022-02-10T04:04:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.