Client-Resolved Generation (CRG), a genera- tion interface that separates server-side generation from the lexical realization of input-derived content, is introduced, which provides a practical interface for privacy-sensitive cloud LLMs by reducing plaintext exposure across both input and output pathways while preserv- ing task utility and server-side model confidentiality.
Abstract
Cloud-based large language models (LLMs) require users to disclose plaintext data to service providers, creating privacy risks in sensitive domains. Existing privacy-preserving approaches often trade utility for protection, incur substantial computational or communication overhead, remain vulnerable to reconstruction from intermediate representations, or protect only a subset of the training and inference pipeline. We introduce Client-Resolved Generation (CRG), a genera- tion interface that separates server-side generation from the lexical realization of input-derived content. The client transmits only pooled and noise-perturbed rep- resentations, while input-derived output content is represented using request-local positional references and resolved to its original strings only on the client. This interface protects private input and input-derived output content during both train- ing and inference while allowing the service provider to keep its proprietary model parameters hidden from the client. At the same time, exact lexical reuse remains possible without directly exposing the reused content on the provider-visible gen- eration path. We evaluate CRG on medical and document-grounded QA, sensi- tive identifier transfer, and tool calling, together with reconstruction and raw-logit leakage analyses. On SealTools, CRG improves complete-call exact match from 57.3% to 79.9% over the input-privacy framework PPFT, with larger gains as more required output content can be resolved through references. Together, these results show that CRG provides a practical interface for privacy-sensitive cloud LLMs by reducing plaintext exposure across both input and output pathways while preserv- ing task utility and server-side model confidentiality.
Cloud-based Large Language Model (LLM) inference services typically require users to submit plain-text inputs, thereby posing severe privacy risks. Existing privacy-preserving paradigms are mostly task-specific and often necessitate pervasive modifications to the entire server-side model. This reliance introduces subst...
Wentao Zhong, Yu-Ting Li, Di-Cong Yu et al.· IEEE Transactions on Informa...· 0 citations
As Retrieval-Augmented Generation (RAG) brings Large Language Models (LLMs) into contact with proprietary and user-specific knowledge bases in sensitive domains, protecting the privacy of both queries and knowledge content becomes a critical requirement. The RAG pipeline, however, exposes sensitive information at two d...
Yuxuan Cai, Chao-Xiang He, Hong-Sheng Hu et al.· IEEE Transactions on Informa...· 0 citations
This work addresses leakage through a learned obfuscate-and-recover scheme that protects participants' private datasets while still allowing an independently deployable model to be trained on the server side, making split-based federated LLM fine-tuning practically viable.
Heng Jin, Chao-Yu Zhang, He-Xuan Yu et al.· 1 citation
CoVeil is proposed, a defense mechanism which dynamically optimizes transmitted signals to suppress leakage during decoding time while preserving the collaborative quality, and consistently improves the privacy-utility trade-off over existing baselines by reducing data leakage.
Ke-Jia Zhang, Tianyuan Zou, Zi-Xuan Gu et al.· 0 citations
This paper introduces the Sensitive Entity Alias Generator (SEAG), a privacy-preserving framework that empowers users to utilize powerful third-party generators without disclosing sensitive information and demonstrates the success of the SEAG framework.
Saleh Almohaimeed, Saad Almohaimeed, Mousa Jari et al.· 0 citations
This work proposes ReGap, a data-free attack that recovers private associations using task structure, filters them by answer-token likelihood, and updates the target model via low-rank adaptation, which requires neither target answers nor auxiliary genuine private supervision.
Jian-Hong Li, Jia-Hao Chen, Yuwen Pu et al.· 0 citations