PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration

• URL: http://arxiv.org/abs/2511.22788v1
• Date: Thu, 27 Nov 2025 22:32:33 GMT
• Title: PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration
• Authors: Junfei Zhan, Haoxun Shen, Zheng Lin, Tengjiao He,
• Abstract summary: 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.
• Score: 8.776463501718737
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) demonstrate impressive capabilities in natural language understanding and generation, but incur high communication overhead and privacy risks in cloud deployments, while facing compute and memory constraints when confined to edge devices. Cloud-edge inference has emerged as a promising paradigm for improving privacy in LLM services by retaining sensitive computations on local devices. However, existing cloud-edge inference approaches apply uniform privacy protection without considering input sensitivity, resulting in unnecessary perturbation and degraded utility even for non-sensitive tokens. To address this limitation, we propose Privacy-aware Routing for Inference with Semantic Modulation (PRISM), a context-aware framework that dynamically balances privacy and inference quality. 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, which is then refined by the edge-side small language model (SLM) using local context. Our results show that PRISM consistently achieves superior privacy-utility trade-offs across various scenarios, reducing energy consumption and latency to 40-50% of baseline methods such as Uniform and Selective LDP, while maintaining high output quality under strong privacy constraints. These findings are validated through comprehensive evaluations involving realistic prompts, actual energy measurements, and heterogeneous cloud-edge model deployments.

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)
• NeuroFilter: Privacy Guardrails for Conversational LLM Agents [50.75206727081996]
  This work addresses the computational challenge of enforcing privacy for agentic Large Language Models (LLMs)<n>NeuroFilter is a guardrail framework that operationalizes contextual integrity by mapping norm violations to simple directions in the model's activation space.<n>A comprehensive evaluation across over 150,000 interactions, covering models from 7B to 70B parameters, illustrates the strong performance of NeuroFilter.
  arXiv  Detail & Related papers  (2026-01-21T05:16:50Z)
• Design and Optimization of Cloud Native Homomorphic Encryption Workflows for Privacy-Preserving ML Inference [0.0]
  Homomorphic Encryption (HE) has emerged as a compelling technique that enables cryptographic computation on encrypted data.<n>The integration of HE within large scale cloud native pipelines remains constrained by high computational overhead, orchestration complexity, and model compatibility issues.<n>This paper presents a systematic framework for the design and optimization of cloud native homomorphic encryption that support privacy ML inference.
  arXiv  Detail & Related papers  (2025-10-28T15:13:32Z)
• ALPINE: A Lightweight and Adaptive Privacy-Decision Agent Framework for Dynamic Edge Crowdsensing [34.752121524751466]
  ALPINE is a lightweight, adaptive framework that empowers terminal devices to adjust differential privacy levels in real time.<n>Based on environmental risk assessments, we design a reward function that balances privacy gains, data utility and energy cost.<n>Both the collaborative risk model and pretrained TD3-based agent are designed for low-overhead deployment.
  arXiv  Detail & Related papers  (2025-10-20T05:03:25Z)
• DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models [17.265217612125905]
  DP-FedLoRA is a privacy-enhanced federated fine-tuning framework.<n>It integrates LoRA-based adaptation with differential privacy in a communication-efficient setting.<n>We show that DP-FedLoRA delivers competitive performance while offering strong privacy guarantees.
  arXiv  Detail & Related papers  (2025-09-11T02:16:34Z)
• Cloud-Device Collaborative Agents for Sequential Recommendation [36.05863003744828]
  Large language models (LLMs) have enabled agent-based recommendation systems with strong semantic understanding and flexible reasoning capabilities.<n>LLMs offer powerful personalization, but they often suffer from privacy concerns, limited access to real-time signals, and scalability bottlenecks.<n>We propose a novel Cloud-Device collaborative framework for sequential Recommendation, powered by dual agents.
  arXiv  Detail & Related papers  (2025-09-01T15:28:11Z)
• RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewriting [17.294176570269]
  We propose a reinforcement learning framework that fine-tunes a large language model (LLM) using a composite reward function.<n>The privacy reward combines semantic cues with structural patterns derived from a minimum spanning tree (MST) over latent representations.<n> Empirical results show that the proposed method significantly enhances author obfuscation and privacy metrics without degrading semantic quality.
  arXiv  Detail & Related papers  (2025-08-25T04:38:19Z)
• CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering [80.54309860395763]
  CoSteer is a novel collaborative framework that enables decoding-time personalization through localized delta steering.<n>We formulate token-level optimization as an online learning problem, where local delta vectors dynamically adjust the remote LLM's logits.<n>This approach preserves privacy by transmitting only the final steered tokens rather than raw data or intermediate vectors.
  arXiv  Detail & Related papers  (2025-07-07T08:32:29Z)
• PWC-MoE: Privacy-Aware Wireless Collaborative Mixture of Experts [59.5243730853157]
  Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns.<n>Small language models (SLMs) running locally enhance privacy but suffer from limited performance on complex tasks.<n>We propose a privacy-aware wireless collaborative mixture of experts (PWC-MoE) framework to balance computational cost, performance, and privacy protection under bandwidth constraints.
  arXiv  Detail & Related papers  (2025-05-13T16:27:07Z)
• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• Split-and-Denoise: Protect large language model inference with local differential privacy [2.572566198588905]
  Split-N-Denoise (SnD) is a private inference framework that splits the model to execute the token embedding layer on the client side at minimal computational cost. We show SnD's effectiveness in optimizing the privacy-utility tradeoff across various LLM architectures and diverse downstream tasks.
  arXiv  Detail & Related papers  (2023-10-13T14:17:33Z)
• Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations [57.20885629270732]
  We consider privacy aspects of wireless federated learning with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server.
  arXiv  Detail & Related papers  (2022-10-05T13:13:35Z)

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.