AI News HubLIVE
原文

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

This paper presents the first unified survey of membership inference and data contamination under the Pretraining Data Exposure (PDE) framework, formalizing exposure levels, reviewing attack and defense methods, synthesizing empirical findings, and highlighting open challenges and future directions.

Article intelligence

InvestorsAdvanced

Key points

  • Pretraining Data Exposure (PDE) determines if specific data appears in an LLM's pretraining corpus, crucial for evaluation integrity and privacy.
  • This paper unifies the study of data contamination and membership inference for the first time under the PDE framework.
  • It formalizes PDE across exposure levels, reviews attack/defense methods, and synthesizes empirical results.

Why it matters

This matters because pretraining Data Exposure (PDE) determines if specific data appears in an LLM's pretraining corpus, crucial for evaluation integrity and privacy.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.26133] Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

[Submitted on 21 May 2026]

Title:Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

View a PDF of the paper titled Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications, by Ziyi Tong and 2 other authors

View PDF

Abstract:Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure (PDE) increase due to the scale and opacity of training datasets.

PDE refers to determining whether specific data appeared in an LLM's pretraining corpus. It is critical for ensuring evaluation integrity and protecting privacy, intersecting two key areas: data contamination and membership inference. Though conceptually related, these areas have often been studied in isolation. This paper offers the first unified survey of both under the PDE framework. We formalize PDE across exposure levels, review attack and defense methods, synthesize empirical findings, and highlight open challenges and future research directions.

Comments: accepted by NLDB 2025

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as: arXiv:2605.26133 [cs.CL]

(or arXiv:2605.26133v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.26133

arXiv-issued DOI via DataCite

Related DOI:

https://doi.org/10.1007/978-3-031-97144-0_14

DOI(s) linking to related resources

Submission history

From: Ziyi Tong [view email] [v1] Thu, 21 May 2026 10:32:33 UTC (61 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications, by Ziyi Tong and 2 other authors

View PDF

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-05

Change to browse by:

cs cs.AI cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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?)