PulseAugur
EN
LIVE 07:23:17

New methods enhance LLM privacy for prompts, adaptation, and RAG

By PulseAugur Editorial · [4 sources] ·

Researchers have developed three distinct methods to enhance privacy in large language models (LLMs). SharedRequest offers a model-agnostic framework that mixes prompts with noisy variants to obscure sensitive information at the batch level, improving utility and reducing inference costs. Echelon provides a boundary-first training architecture that enforces device-level model-state non-export, enabling auditable, aggregate-only adaptation across privacy boundaries. Privacy-Aware Decoding (PAD) is a lightweight, inference-time defense that injects calibrated noise into token logits during generation, specifically for Retrieval-Augmented Generation (RAG) systems, to mitigate private information leakage while preserving response utility. AI

IMPACT These advancements offer improved privacy guarantees for LLM users and developers, potentially enabling wider adoption in sensitive domains.

RANK_REASON Multiple research papers proposing novel methods for LLM privacy.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

COVERAGE [4]

  1. arXiv cs.AI TIER_1 English(EN) · Peihua Mai, Xuanrong Gao, Youlong Ding, Xianglong Du, Wei Liu, Yan Pang ·

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

    arXiv:2606.05004v1 Announce Type: cross Abstract: 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 utilit…

  2. arXiv cs.AI TIER_1 English(EN) · Yan Pang ·

    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 …

  3. arXiv cs.AI TIER_1 English(EN) · Hina Dixit, Punit Kumar, Irene Tenison, Nevasini Sasikumar ·

    Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries

    arXiv:2606.02958v1 Announce Type: cross Abstract: Cross-organization language-model adaptation increasingly faces hard governance constraints: in many deployments, device-level model state-parameters, activations, optimizer state, and per-device updates-cannot be exported outside…

  4. arXiv cs.CL TIER_1 English(EN) · Haoran Wang, Xiongxiao Xu, Baixiang Huang, Kai Shu ·

    Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation

    arXiv:2508.03098v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sources. However, when retrieval involves private or sensitive data, RAG systems ar…

RELATED ENTITIES

RELATED TOPICS