TY - JOUR
T1 - Achieving Privacy-Preserving and Communication-Efficient Federated Learning in Internet of Unmanned Agents
AU - Xu, Yuhua
AU - Hu, Chenfei
AU - Xu, Zihao
AU - Zhang, Chuan
AU - Fu, Shan
AU - Cheng, Nan
AU - Yang, Song
AU - Zhu, Liehuang
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2026
Y1 - 2026
N2 - With the rapid advancement of ubiquitous connectivity, the internet of unmanned agents (IUAs) has emerged as a promising paradigm for distributed intelligent perception and decision-making. In such systems, numerous unmanned agents collaboratively collect environmental data to support coordinated tasks. To preserve data privacy, federated learning (FL), as a decentralized machine learning framework, enables collaborative training of a global model across agents without directly exchanging raw data. However, FL faces several critical challenges in IUA environments, including high communication overhead under constrained wireless bandwidth, potential privacy leakage from shared model parameters, and agent dropouts caused by unstable connectivity. To address these challenges, we propose PPE-FL, a privacy-preserving and communication-efficient FL scheme designed for IUA scenarios. PPE-FL replaces conventional high-dimensional gradient uploads with lightweight ranking-based votes, substantially reducing communication overhead. Then, we design an obfuscation mechanism to protect the privacy of locally generated ranking-based votes, safeguarding both raw data and intermediate parameters. Furthermore, PPE-FL supports mask reconstruction through partial interactions among online unmanned agents, enabling robust aggregation under dynamic network conditions. Experimental results demonstrate that the proposed PPE-FL reduces communication costs by 89.5% compared to VCD-FL and by 87.7% compared to PPML, while maintaining model accuracy and privacy protection.
AB - With the rapid advancement of ubiquitous connectivity, the internet of unmanned agents (IUAs) has emerged as a promising paradigm for distributed intelligent perception and decision-making. In such systems, numerous unmanned agents collaboratively collect environmental data to support coordinated tasks. To preserve data privacy, federated learning (FL), as a decentralized machine learning framework, enables collaborative training of a global model across agents without directly exchanging raw data. However, FL faces several critical challenges in IUA environments, including high communication overhead under constrained wireless bandwidth, potential privacy leakage from shared model parameters, and agent dropouts caused by unstable connectivity. To address these challenges, we propose PPE-FL, a privacy-preserving and communication-efficient FL scheme designed for IUA scenarios. PPE-FL replaces conventional high-dimensional gradient uploads with lightweight ranking-based votes, substantially reducing communication overhead. Then, we design an obfuscation mechanism to protect the privacy of locally generated ranking-based votes, safeguarding both raw data and intermediate parameters. Furthermore, PPE-FL supports mask reconstruction through partial interactions among online unmanned agents, enabling robust aggregation under dynamic network conditions. Experimental results demonstrate that the proposed PPE-FL reduces communication costs by 89.5% compared to VCD-FL and by 87.7% compared to PPML, while maintaining model accuracy and privacy protection.
KW - Communication efficiency
KW - federated learning (FL)
KW - internet of unmanned agents (IUAs)
KW - privacy protection
UR - https://www.scopus.com/pages/publications/105022645863
U2 - 10.1109/JIOT.2025.3635164
DO - 10.1109/JIOT.2025.3635164
M3 - Article
AN - SCOPUS:105022645863
SN - 2327-4662
VL - 13
SP - 6059
EP - 6074
JO - IEEE Internet of Things Journal
JF - IEEE Internet of Things Journal
IS - 4
ER -