Lune

EMNLP Findings2025

LLMs are Privacy Erasable

Zipeng Ye, Wenjian Luo

Abstract

The capabilities of large language models (LLMs) are advancing at an remarkable pace, along with a surge in cloud services that are powered by LLMs. Their convenience has gradually transformed the routines people work. However, for services such as document summarizing, editing, and so on, users need to upload relevant files or context to obtain the desired services, which may inadvertently expose their privacy. This paper aims to address the challenging balance between the convenience of LLMs services and user privacy concerns. Specifically, based on the structural and functional characteristics of LLMs, we have developed a strategy that safeguards user prompt while accessing LLM cloud services, even in scenarios where advanced reconstruction attacks are adopted. We comprehensively evaluate the efficacy of our method across prominent LLM benchmarks. The empirical results show that our method not only effectively thwarts reconstruction attacks but also, in certain tasks, even improves model performance, surpassing the outcomes reported in official model cards.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on28

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  3. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  4. Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
  5. Membership Inference Attacks Against Machine Learning ModelsReza Shokri, Marco Stronati, Congzheng Song, Vitaly ShmatikovS&P 2017 · 5,137 citations

Related papers

  1. Reconstruction Attack-Resistant Inference Paradigm for LLM Cloud ServicesZipeng Ye, Wenjian Luo, Qi Zhou, Yubo TangAAAI 2026
  2. Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT ModelsJunjie Chu, Zeyang Sha, Michael Backes, Yang ZhangEMNLP 2024 · 3 citations
  3. Prompt Inference Attack on Distributed Large Language Model Inference FrameworksXinjian Luo, Ting Yu, Xiaokui XiaoCCS 2025
  4. Hidden No More: Attacking and Defending Private Third-Party LLM InferenceRahul Krishna Thomas, Louai Zahran, Erica Choi, Akilesh Potti et al.ICML 2025
  5. When Cache Poisoning Meets LLM Systems: Semantic Cache Poisoning and Its CountermeasuresGuanlong Wu, Taojie Wang, Yao Zhang, Zheng Zhang et al.NDSS 2026 · 6 citations
Dusk over the sea between two cliffs drawn in fine vertical lines