Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Adaptive Client Selection in Federated Learning: A Network Anomaly Detection Use Case

Conference ·
 [1];  [1];  [1]
  1. University of Texas at El Paso,Department of Computer Science,El Paso,USA

Federated Learning (FL) has become a ubiquitous approach for training machine learning models on decentralized data, addressing the myriad privacy concerns inherent in traditional centralized methods. However, the efficiency of FL depends on effective client selection and robust privacy preservation mechanisms. Inadequate client selection may lead to suboptimal model performance, while insufficient privacy measures risk exposing sensitive data. This paper proposes a client selection framework for FL that integrates differential privacy and fault tolerance. Our adaptive approach dynamically adjusts the number of selected clients based on model performance and system constraints, ensuring privacy through calibrated noise addition. We evaluate our method on a network anomaly detection use case using the UNSW-NB15 and ROAD datasets. Results show up to a 7% increase in accuracy and a 25% reduction in training time compared to FedL2P. Moreover, we highlight the trade-offs between privacy budgets and model performance, with higher privacy budgets reducing noise and improving accuracy. Our fault tolerance mechanism, while causing a slight performance drop, enhances robustness to client failures. Statistical validation using Mann-Whitney U tests confirms the significance of these improvements (p < 0.05).

Research Organization:
National Energy Technology Laboratory
Sponsoring Organization:
United States Department of Energy
DOE Contract Number:
FE0032089
OSTI ID:
2583897
Country of Publication:
United States
Language:
English

References (9)

AdaFL: Adaptive Client Selection and Dynamic Contribution Evaluation for Efficient Federated Learning conference April 2024
Client Selection in Hierarchical Federated Learning journal September 2024
Network Anomaly Detection Using Federated Learning conference November 2022
UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set) conference November 2015
How Valuable is Your Data? Optimizing Client Recruitment in Federated Learning journal October 2024
Active Client Selection for Clustered Federated Learning journal November 2024
CriticalFL: A Critical Learning Periods Augmented Client Selection Framework for Efficient Federated Learning conference August 2023
Checkpointing Strategies to Tolerate Non-Memoryless Failures on HPC Platforms journal March 2024
A comprehensive guide to CAN IDS data and introduction of the ROAD dataset journal January 2024

Similar Records

Efficient Client Selection in Federated Learning
Conference · Thu Jan 09 23:00:00 EST 2025 · OSTI ID:2583901

Reducing Communication Overhead in Federated Learning for Network Anomaly Detection with Adaptive Client Selection
Conference · Mon May 19 00:00:00 EDT 2025 · OSTI ID:2583896

Federated Learning for Efficient Condition Monitoring and Anomaly Detection in Industrial Cyber-Physical Systems
Conference · Sun Feb 16 23:00:00 EST 2025 · OSTI ID:2583898

Related Subjects