论文研究
arxiv.org ·
只付你必须花费的：面向差分隐私 RAG 的按需隐私预算支付
该 arXiv 论文（cs.CR）提出 SparsePay-RAG，针对现有 DP-RAG 框架隐私预算快速耗尽、预算支出与模型对私有数据实际依赖不匹配的问题，以“只付必须花费的”为核心原则：以公开信息作为零隐私先验，仅对私有增量收取隐私预算。具体做法包括用公开主题引导聚类缩小检索范围、通过等渗跨层轨迹拟合在不消耗隐私成本的前提下自适应控制私有访问频率、用 DP 对比解码压缩单次访问预算。摘要称在强隐私约束下其隐私-效用权衡优于基线，但未提供具体数据集与量化结果。
AI推荐理由 arXiv 新论文（cs.CR），提出 SparsePay-RAG，针对差分隐私 RAG 中隐私预算被快速耗尽的问题，以“只付必须花费的”为原则：用公开信息作为零隐私先验，仅对私有增量计费，并通过公开主题引导聚类缩小检索范围、等渗跨层轨迹拟合自适应控制私有访问频率、DP 对比解码压缩单次访问预算。摘要称在强隐私约束下取得更优的隐私-效用权衡，但未给出具体数据集、指标数值或与基线的量化对比，效果仍需正文验证。属于方法层面的新思路，对隐私敏感场景下的 RAG 部署有参考价值。
72
正文
Computer Science > Cryptography and Security
arXiv:2609.27406 (cs)
[Submitted on 23 Sep 2026]
Title:Only Pay What You Must Spend: On-Demand Privacy Budget Payment for Differentially Private RAG
Authors:Zhonghao Sun, Zhiliang Tian, Xinyue Fang, Shuo Ma, Juhua Zhang, Yiping Song, Dongsheng Li
View a PDF of the paper titled Only Pay What You Must Spend: On-Demand Privacy Budget Payment for Differentially Private RAG, by Zhonghao Sun and 6 other authors
View PDF
HTML (experimental)
Abstract:Deploying large language models (LLMs) on sensitive data via Retrieval-Augmented Generation (RAG) introduces severe privacy risks. Recent studies apply Differential Privacy (DP) to LLMs with RAG for formal privacy guarantees. However, existing DP-RAG frameworks rapidly exhaust the privacy budget. Although recent efforts attempt to save the budget by narrowing the retrieval scope or sparsifying private generation, these methods themselves cumulatively consume the budget, whereas they could actually rely merely on public information or at a negligible one-time privacy cost. This mismatch fails to align budget expenditure with the model's actual reliance on private data, causing substantial waste on operations that require no private access. To address this, we propose SparsePay-RAG, adopting "only pay what you must spend" as its core principle. Using public information as a zero-privacy prior, it charges the privacy budget only for the private increment. Specifically, SparsePay-RAG narrows the retrieval scope via public topic-guided clustering, adaptively controls private access frequency without privacy cost through isotonic cross-layer trajectory fitting, and compresses per-access budget via DP contrastive decoding. Under strong privacy constraints, experiments show SparsePay-RAG achieves superior privacy-utility trade-offs over baselines.
Comments:
Subjects:
Cryptography and Security (cs.CR); Digital Libraries (cs.DL)
Cite as:
arXiv:2609.27406 [cs.CR]
(or
arXiv:2609.27406v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2609.27406
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Fang Xinyue [view email]
[v1]
Wed, 23 Sep 2026 06:20:17 UTC (265 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Only Pay What You Must Spend: On-Demand Privacy Budget Payment for Differentially Private RAG, by Zhonghao Sun and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CR
new
|
recent
| 2026-09
Change to browse by:
cs
cs.DL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)