做LLM隐私保护的团队终于有了一个无需改模型、不牺牲太多效用的实用方案——批量推理还能省成本，做API服务的开发者值得关注。
SharedRequest 是一种针对大语言模型（LLM）的隐私保护推理框架，通过将原始提示与噪声变体混合，并在批量级别进行语义分组，来隐藏敏感信息。该方法无需修改模型架构或访问模型参数，兼容任何LLM。实验表明，与差分隐私基线相比，SharedRequest 的效用提升超过20%，且共享提示机制使查询成本降低最多5倍。该框架解决了现有方法在效用、效率和兼容性上的权衡问题。
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
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 $5\times$ compared to non-batched inference.