# SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

arXiv: https://arxiv.org/abs/2606.05004 · HTML: https://mlsanity.com/paper/2606.05004/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness](https://mlsanity.com/paper/2010.01285/) (2020)
- [DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass](https://mlsanity.com/paper/2309.06746/) (2023)
- [The Limits of Word Level Differential Privacy](https://mlsanity.com/paper/2205.02130/) (2022)
- [Locally Differentially Private Document Generation Using Zero Shot Prompting](https://mlsanity.com/paper/2310.16111/) (2023)
- [A Customized Text Sanitization Mechanism with Differential Privacy](https://mlsanity.com/paper/2207.01193/) (2022)
- [Named Entity Recognition and Classification on Historical Documents: A Survey](https://mlsanity.com/paper/2109.11406/) (2021)
- [Prio: Private, Robust, and Scalable Computation of Aggregate Statistics](https://mlsanity.com/paper/1703.06255/) (2017)
- [Towards Differentially Private Text Representations](https://mlsanity.com/paper/2006.14170/) (2020)
- [ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation](https://mlsanity.com/paper/2511.11483/) (2025)
- [Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets](https://mlsanity.com/paper/2105.11653/) (2021)
- [SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC](https://mlsanity.com/paper/2401.00793/) (2024)
- [DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis](https://mlsanity.com/paper/2510.25237/) (2025)
- [An Ensemble Framework for Unbiased Language Model Watermarking](https://mlsanity.com/paper/2509.24043/) (2025)
- [POET: Preference Optimization for Enhanced Text-to-Image Generation](https://mlsanity.com/paper/2510.12041/) (2025)

## Built on by (most cited first, 1 of 1)

- [DP-MIND: Differentially private memory-guided Long context Inference](https://mlsanity.com/paper/2610.13132/) (2026)

## Abstract (arXiv)

With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue. Existing privacy-preserving inference methods sacrifice either utility or efficiency, and often require model-specific modifications that limit their compatibility. In this paper, we propose SharedRequest, a model-agnostic framework for privacy-preserving LLM inference that reformulates privacy protection at the batch level rather than the individual-prompt level. The key idea is to obscure sensitive information by mixing original prompts with noisy variants, while grouping semantically equivalent instructions to amortize the inference cost over a large batch of queries with minimal impact on LLM response quality. This design is independent of the LLM architecture, requiring no access to model parameters or architectural modification. Empirical results demonstrate that SharedRequest achieves over 20% higher utility compared to prior differential privacy baselines, and its shared-prompt mechanism reduces query cost by up to 5× compared to non-batched inference.