Towards Privacy-Preserving LLM Inference via Collaborative Obfuscation (Technical Report)

• URL: http://arxiv.org/abs/2603.01499v1
• Date: Mon, 02 Mar 2026 06:16:36 GMT
• Title: Towards Privacy-Preserving LLM Inference via Collaborative Obfuscation (Technical Report)
• Authors: Yu Lin, Qizhi Zhang, Wenqiang Ruan, Daode Zhang, Jue Hong, Ye Wu, Hanning Xia, Yunlong Mao, Sheng Zhong,
• Abstract summary: AloePri is the first privacy-preserving LLM inference method for industrial applications.<n>We show that AloePri causes accuracy loss of 0.0%3.5% and exhibits efficiency equivalent to that of plaintext inference.
• Score: 11.45459291503604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid development of large language models (LLMs) has driven the widespread adoption of cloud-based LLM inference services, while also bringing prominent privacy risks associated with the transmission and processing of private data in remote inference. For privacy-preserving LLM inference technologies to be practically applied in industrial scenarios, three core requirements must be satisfied simultaneously: (1) Accuracy and efficiency losses should be minimized to mitigate degradation in service experience. (2) The inference process can be run on large-scale clusters consist of heterogeneous legacy xPUs. (3) Compatibility with existing LLM infrastructures should be ensured to reuse their engineering optimizations. To the best of our knowledge, none of the existing privacy-preserving LLM inference methods satisfy all the above constraints while delivering meaningful privacy guarantees. In this paper, we propose AloePri, the first privacy-preserving LLM inference method for industrial applications. AloePri protects both the input and output data by covariant obfuscation, which jointly transforms data and model parameters to achieve better accuracy and privacy. We carefully design the transformation for each model component to ensure inference accuracy and data privacy while keeping full compatibility with existing infrastructures of Language Model as a Service. AloePri has been integrated into an industrial system for the evaluation of mainstream LLMs. The evaluation on Deepseek-V3.1-Terminus model (671B parameters) demonstrates that AloePri causes accuracy loss of 0.0%~3.5% and exhibits efficiency equivalent to that of plaintext inference. Meanwhile, AloePri successfully resists state-of-the-art attacks, with less than 5\% of tokens recovered. To the best of our knowledge, AloePri is the first method to exhibit practical applicability to large-scale models in real-world systems.

Related papers

• Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models [39.390624817461905]
  Talaria is a confidential inference framework that partitions the Large Language Models pipeline to protect client data.<n>Talaria executes sensitive, weight-independent operations within a client-controlled Confidential Virtual Machine.<n>Talaria can defend against state-of-the-art token inference attacks, reducing token reconstruction accuracy from over 97.5% to an average of 1.34%.
  arXiv  Detail & Related papers  (2026-02-27T06:37:07Z)
• 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)
• SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks [17.77094760401298]
  We study the vulnerability of fine-tuned large language models to membership inference attacks (MIAs)<n>We propose SOFT, a novel defense technique that mitigates privacy leakage by leveraging influential data selection with an adjustable parameter to balance utility preservation and privacy protection.
  arXiv  Detail & Related papers  (2025-06-12T07:23:56Z)
• Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation [60.81109086640437]
  We propose a novel framework called Federated Retrieval-Augmented Generation (FedE4RAG)<n>FedE4RAG facilitates collaborative training of client-side RAG retrieval models.<n>We apply homomorphic encryption within federated learning to safeguard model parameters.
  arXiv  Detail & Related papers  (2025-04-27T04:26:02Z)
• 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)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models [40.1319651615647]
  We are among the first attempts towards robust and private LLM inference by tightly integrating two disconnected fields: private inference and prompt ensembling.<n>We propose SecPE, which designs efficient fully homomorphic encryption (FHE) counterparts for the core algorithmic building blocks of prompt ensembling.<n>Results show that SecPE maintains high clean accuracy and offers better robustness at the expense of merely $2.5%$ efficiency overhead.
  arXiv  Detail & Related papers  (2025-02-02T16:40:21Z)
• The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility? [54.18519360412294]
  Large Language Models (LLMs) must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility.<n>This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance.<n>We analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model.
  arXiv  Detail & Related papers  (2025-01-20T06:35:01Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• Model-based Large Language Model Customization as Service [45.92528738079333]
  Large Language Model (LLM) services from providers like OpenAI and Google excel at general tasks but often underperform on domain-specific applications.<n>We introduce Llamdex, a novel framework that facilitates LLM customization as a service, where the client uploads pre-trained domain-specific models rather than data.<n> Experiments demonstrate that Llamdex improves domain-specific accuracy by up to 26% over state-of-the-art private data synthesis methods under identical privacy constraints.
  arXiv  Detail & Related papers  (2024-10-14T13:18:20Z)
• InferDPT: Privacy-Preserving Inference for Black-box Large Language Model [66.07752875835506]
  InferDPT is the first practical framework for the privacy-preserving Inference of black-box LLMs.<n>RANTEXT is a novel differential privacy mechanism integrated into the perturbation module of InferDPT.
  arXiv  Detail & Related papers  (2023-10-18T18:00:11Z)
• Theoretically Principled Federated Learning for Balancing Privacy and Utility [61.03993520243198]
  We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters. It can achieve personalized utility-privacy trade-off for each model parameter, on each client, at each communication round in federated learning.
  arXiv  Detail & Related papers  (2023-05-24T13:44:02Z)

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.