@inproceedings{udsa-etal-2026-exploring,
title = "Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning",
author = "Udsa, Tinnakit and
Udomcharoenchaikit, Can and
Payoungkhamdee, Patomporn and
Nutanong, Sarana and
Rattanavipanon, Norrathep",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-short.56/",
pages = "679--693",
ISBN = "979-8-89176-391-3",
abstract = "Federated learning (FL) enables collaborative training without raw data sharing, but still risks training data memorization. Existing FL memorization detection techniques focus on one sample at a time, underestimating more subtle risks of cross-sample memorization. In contrast, recent work on centralized learning (CL) has introduced fine-grained methods to assess memorization across all samples in training data, but these assume centralized access to data and cannot be applied directly to FL. We bridge this gap by proposing a framework that quantifies both intra- and inter-client memorization in FL using fine-grained cross-sample memorization measurement across all clients. Based on this framework, we conduct two studies: (1) measuring subtle memorization across clients and (2) examining key factors that influence memorization, including decoding strategies, prefix length, and FL algorithms. Our findings reveal that FL models do memorize client data, particularly intra-client data, more than inter-client data, with memorization influenced by training and inferencing factors."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="udsa-etal-2026-exploring">
<titleInfo>
<title>Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tinnakit</namePart>
<namePart type="family">Udsa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Udomcharoenchaikit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patomporn</namePart>
<namePart type="family">Payoungkhamdee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarana</namePart>
<namePart type="family">Nutanong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norrathep</namePart>
<namePart type="family">Rattanavipanon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-391-3</identifier>
</relatedItem>
<abstract>Federated learning (FL) enables collaborative training without raw data sharing, but still risks training data memorization. Existing FL memorization detection techniques focus on one sample at a time, underestimating more subtle risks of cross-sample memorization. In contrast, recent work on centralized learning (CL) has introduced fine-grained methods to assess memorization across all samples in training data, but these assume centralized access to data and cannot be applied directly to FL. We bridge this gap by proposing a framework that quantifies both intra- and inter-client memorization in FL using fine-grained cross-sample memorization measurement across all clients. Based on this framework, we conduct two studies: (1) measuring subtle memorization across clients and (2) examining key factors that influence memorization, including decoding strategies, prefix length, and FL algorithms. Our findings reveal that FL models do memorize client data, particularly intra-client data, more than inter-client data, with memorization influenced by training and inferencing factors.</abstract>
<identifier type="citekey">udsa-etal-2026-exploring</identifier>
<location>
<url>https://aclanthology.org/2026.acl-short.56/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>679</start>
<end>693</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
%A Udsa, Tinnakit
%A Udomcharoenchaikit, Can
%A Payoungkhamdee, Patomporn
%A Nutanong, Sarana
%A Rattanavipanon, Norrathep
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-391-3
%F udsa-etal-2026-exploring
%X Federated learning (FL) enables collaborative training without raw data sharing, but still risks training data memorization. Existing FL memorization detection techniques focus on one sample at a time, underestimating more subtle risks of cross-sample memorization. In contrast, recent work on centralized learning (CL) has introduced fine-grained methods to assess memorization across all samples in training data, but these assume centralized access to data and cannot be applied directly to FL. We bridge this gap by proposing a framework that quantifies both intra- and inter-client memorization in FL using fine-grained cross-sample memorization measurement across all clients. Based on this framework, we conduct two studies: (1) measuring subtle memorization across clients and (2) examining key factors that influence memorization, including decoding strategies, prefix length, and FL algorithms. Our findings reveal that FL models do memorize client data, particularly intra-client data, more than inter-client data, with memorization influenced by training and inferencing factors.
%U https://aclanthology.org/2026.acl-short.56/
%P 679-693
Markdown (Informal)
[Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning](https://aclanthology.org/2026.acl-short.56/) (Udsa et al., ACL 2026)
ACL