No Cover Image

Journal article 51 views 3 downloads

Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks

Yangyang Bao Orcid Logo, Cheng Cheng Orcid Logo, Liming Nie Orcid Logo, Junyi Tao Orcid Logo

IEEE Transactions on Cognitive Communications and Networking, Volume: 12, Pages: 2919 - 2936

Swansea University Author: Cheng Cheng Orcid Logo

  • 71251.AAM.pdf

    PDF | Accepted Manuscript

    Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).

    Download (379.95KB)

Check full text

DOI (Published version): 10.1109/tccn.2025.3620369

Abstract

Advancement of unmanned aerial vehicle (UAV) swarm networks presents transformative opportunities for low-altitude surveillance, disaster response, and distributed sensing, where federated large language models (LLMs) enable collaborative learning while preserving data privacy, enhance swarm-level s...

Full description

Published in: IEEE Transactions on Cognitive Communications and Networking
ISSN: 2332-7731
Published: Institute of Electrical and Electronics Engineers (IEEE) 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71251
first_indexed 2026-01-14T12:12:35Z
last_indexed 2026-01-23T04:29:05Z
id cronfa71251
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-01-21T09:54:19.5866509</datestamp><bib-version>v2</bib-version><id>71251</id><entry>2026-01-14</entry><title>Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks</title><swanseaauthors><author><sid>11ddf61c123b99e59b00fa1479367582</sid><ORCID>0000-0003-0371-9646</ORCID><firstname>Cheng</firstname><surname>Cheng</surname><name>Cheng Cheng</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-01-14</date><deptcode>MACS</deptcode><abstract>Advancement of unmanned aerial vehicle (UAV) swarm networks presents transformative opportunities for low-altitude surveillance, disaster response, and distributed sensing, where federated large language models (LLMs) enable collaborative learning while preserving data privacy, enhance swarm-level situational awareness through decentralized knowledge fusion, and support adaptive decision-making across dynamic low-altitude operational environments. However, federated LLM fine-tuning for UAV swarm networks operating in low-altitude settings faces three unresolved security and practical issues: 1) lack of efficient methods to protect parameter security during uplink/downlink transmission under low-altitude communication constraints; 2) absence of effective mechanisms to handle frequent UAV dropouts caused by low-altitude dynamics that may compromise the robustness of federated LLM systems; and 3) constraints in UAVs&#x2019; computing, storage and communication resources under typical low-altitude mission profiles. To address these challenges, this paper proposes a Secure and privacy-preserving federated fine-tuning (SPFF) scheme for low-altitude UAV swarms that enables: efficient and privacy-preserving one-to-many distribution of global parameters for downlink federated fine-tuning; secure and efficient uplink local parameter uploading adapted to low-altitude network conditions; and encrypted-parameter-based global model fine-tuning. The scheme also incorporates an efficient supervised key update mechanism to address UAV dropout issues common in low-altitude operations. Moreover, we design a delegable extensional SPFF (DE-SPFF) scheme that employs proxy re-encryption to allow UAVs to delegate tasks to other drones before exiting the federated fine-tuning process in volatile low-altitude environments, while providing public verifiability for re-encryption operations performed by semi-trusted edge nodes. Formal security proofs demonstrate the security of the proposed schemes under low-altitude threat models. Theoretical analysis and experimental results confirm their superiority and practicality for low-altitude UAV swarm applications.</abstract><type>Journal Article</type><journal>IEEE Transactions on Cognitive Communications and Networking</journal><volume>12</volume><journalNumber/><paginationStart>2919</paginationStart><paginationEnd>2936</paginationEnd><publisher>Institute of Electrical and Electronics Engineers (IEEE)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2332-7731</issnElectronic><keywords>Autonomous aerial vehicles, Security, Encryption, Federated learning, Data models, Computational efficiency, Vehicle dynamics, Training, Faces, Costs</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-12-31</publishedDate><doi>10.1109/tccn.2025.3620369</doi><url>https://doi.org/10.1109/TCCN.2025.3620369</url><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>This work is sponsored by National Natural Science Foundation of China (NSFC) (Grant Number: W2412110), UKRI (Grant Number: EP/W020408/1), Doctoral Training Centre at Swansea University (Grant Number: RS718), and China Postdoctoral Science Foundation (Grant Number: 2024M753597).</funders><projectreference/><lastEdited>2026-01-21T09:54:19.5866509</lastEdited><Created>2026-01-14T12:03:53.2435953</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Yangyang</firstname><surname>Bao</surname><orcid>0000-0002-0432-0015</orcid><order>1</order></author><author><firstname>Cheng</firstname><surname>Cheng</surname><orcid>0000-0003-0371-9646</orcid><order>2</order></author><author><firstname>Liming</firstname><surname>Nie</surname><orcid>0000-0002-6058-1586</orcid><order>3</order></author><author><firstname>Junyi</firstname><surname>Tao</surname><orcid>0009-0000-1113-3616</orcid><order>4</order></author></authors><documents><document><filename>71251__36065__56a237464ba84a7f846c19779278fae1.pdf</filename><originalFilename>71251.AAM.pdf</originalFilename><uploaded>2026-01-21T09:50:23.0817834</uploaded><type>Output</type><contentLength>389070</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-01-21T09:54:19.5866509 v2 71251 2026-01-14 Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks 11ddf61c123b99e59b00fa1479367582 0000-0003-0371-9646 Cheng Cheng Cheng Cheng true false 2026-01-14 MACS Advancement of unmanned aerial vehicle (UAV) swarm networks presents transformative opportunities for low-altitude surveillance, disaster response, and distributed sensing, where federated large language models (LLMs) enable collaborative learning while preserving data privacy, enhance swarm-level situational awareness through decentralized knowledge fusion, and support adaptive decision-making across dynamic low-altitude operational environments. However, federated LLM fine-tuning for UAV swarm networks operating in low-altitude settings faces three unresolved security and practical issues: 1) lack of efficient methods to protect parameter security during uplink/downlink transmission under low-altitude communication constraints; 2) absence of effective mechanisms to handle frequent UAV dropouts caused by low-altitude dynamics that may compromise the robustness of federated LLM systems; and 3) constraints in UAVs’ computing, storage and communication resources under typical low-altitude mission profiles. To address these challenges, this paper proposes a Secure and privacy-preserving federated fine-tuning (SPFF) scheme for low-altitude UAV swarms that enables: efficient and privacy-preserving one-to-many distribution of global parameters for downlink federated fine-tuning; secure and efficient uplink local parameter uploading adapted to low-altitude network conditions; and encrypted-parameter-based global model fine-tuning. The scheme also incorporates an efficient supervised key update mechanism to address UAV dropout issues common in low-altitude operations. Moreover, we design a delegable extensional SPFF (DE-SPFF) scheme that employs proxy re-encryption to allow UAVs to delegate tasks to other drones before exiting the federated fine-tuning process in volatile low-altitude environments, while providing public verifiability for re-encryption operations performed by semi-trusted edge nodes. Formal security proofs demonstrate the security of the proposed schemes under low-altitude threat models. Theoretical analysis and experimental results confirm their superiority and practicality for low-altitude UAV swarm applications. Journal Article IEEE Transactions on Cognitive Communications and Networking 12 2919 2936 Institute of Electrical and Electronics Engineers (IEEE) 2332-7731 Autonomous aerial vehicles, Security, Encryption, Federated learning, Data models, Computational efficiency, Vehicle dynamics, Training, Faces, Costs 31 12 2026 2026-12-31 10.1109/tccn.2025.3620369 https://doi.org/10.1109/TCCN.2025.3620369 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Not Required This work is sponsored by National Natural Science Foundation of China (NSFC) (Grant Number: W2412110), UKRI (Grant Number: EP/W020408/1), Doctoral Training Centre at Swansea University (Grant Number: RS718), and China Postdoctoral Science Foundation (Grant Number: 2024M753597). 2026-01-21T09:54:19.5866509 2026-01-14T12:03:53.2435953 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Yangyang Bao 0000-0002-0432-0015 1 Cheng Cheng 0000-0003-0371-9646 2 Liming Nie 0000-0002-6058-1586 3 Junyi Tao 0009-0000-1113-3616 4 71251__36065__56a237464ba84a7f846c19779278fae1.pdf 71251.AAM.pdf 2026-01-21T09:50:23.0817834 Output 389070 application/pdf Accepted Manuscript true Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention). true eng https://creativecommons.org/licenses/by/4.0/
title Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks
spellingShingle Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks
Cheng Cheng
title_short Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks
title_full Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks
title_fullStr Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks
title_full_unstemmed Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks
title_sort Enabling Privacy-Preserving and Drop-Out Resilient Federated LLM Fine-Tuning for the Low-Altitude UAV Swarm Networks
author_id_str_mv 11ddf61c123b99e59b00fa1479367582
author_id_fullname_str_mv 11ddf61c123b99e59b00fa1479367582_***_Cheng Cheng
author Cheng Cheng
author2 Yangyang Bao
Cheng Cheng
Liming Nie
Junyi Tao
format Journal article
container_title IEEE Transactions on Cognitive Communications and Networking
container_volume 12
container_start_page 2919
publishDate 2026
institution Swansea University
issn 2332-7731
doi_str_mv 10.1109/tccn.2025.3620369
publisher Institute of Electrical and Electronics Engineers (IEEE)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url https://doi.org/10.1109/TCCN.2025.3620369
document_store_str 1
active_str 0
description Advancement of unmanned aerial vehicle (UAV) swarm networks presents transformative opportunities for low-altitude surveillance, disaster response, and distributed sensing, where federated large language models (LLMs) enable collaborative learning while preserving data privacy, enhance swarm-level situational awareness through decentralized knowledge fusion, and support adaptive decision-making across dynamic low-altitude operational environments. However, federated LLM fine-tuning for UAV swarm networks operating in low-altitude settings faces three unresolved security and practical issues: 1) lack of efficient methods to protect parameter security during uplink/downlink transmission under low-altitude communication constraints; 2) absence of effective mechanisms to handle frequent UAV dropouts caused by low-altitude dynamics that may compromise the robustness of federated LLM systems; and 3) constraints in UAVs’ computing, storage and communication resources under typical low-altitude mission profiles. To address these challenges, this paper proposes a Secure and privacy-preserving federated fine-tuning (SPFF) scheme for low-altitude UAV swarms that enables: efficient and privacy-preserving one-to-many distribution of global parameters for downlink federated fine-tuning; secure and efficient uplink local parameter uploading adapted to low-altitude network conditions; and encrypted-parameter-based global model fine-tuning. The scheme also incorporates an efficient supervised key update mechanism to address UAV dropout issues common in low-altitude operations. Moreover, we design a delegable extensional SPFF (DE-SPFF) scheme that employs proxy re-encryption to allow UAVs to delegate tasks to other drones before exiting the federated fine-tuning process in volatile low-altitude environments, while providing public verifiability for re-encryption operations performed by semi-trusted edge nodes. Formal security proofs demonstrate the security of the proposed schemes under low-altitude threat models. Theoretical analysis and experimental results confirm their superiority and practicality for low-altitude UAV swarm applications.
published_date 2026-12-31T05:33:38Z
_version_ 1856805817351667712
score 11.096027

Similar Items