Personalized Federated Learning for Detecting False Data Injection Attacks in Power Grids

In the context of security protection against false data injection attacks (FDIAs) in power grids, traditional federated learning effectively utilizes decentralized data resources for distributed training and achieves global collaboration. However, during the model aggregation process, it often overlooks or drowns out local sparse key features, significantly increasing the risk of missed detection of specific attack patterns. To address this issue, this paper proposes a personalized detection framework based on federated learning. Initially, the bidirectional transformer detection (BTD) model detection algorithm is deployed on the client side and trained on local data. Subsequently, through personalized federated learning, the client dynamically combines the weights of the global and local models to generate a personalized detection model. The framework employs a collaborative optimization mechanism of “global knowledge sharing and local feature adaptation” to effectively mitigate the feature drowning problem while strictly safeguarding data privacy. Compared to existing methods, this approach significantly enhances detection accuracy and robustness against differentiated attack patterns, thereby establishing a more reliable security defense system for smart grids.

• Publication year

  2026

• Venue

  Concurrency and Computation

• Publication date

  2026-01-01

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1002/cpe.70543
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Reinforcement Learning-Based False Data Injection Attacks in Smart Grids

  2025cited by this paper
• Trustworthy cyber-physical power systems using AI: dueling algorithms for PMU anomaly detection and cybersecurity

  2024cited by this paper
• Detection of False Data Injection Attacks in Distribution Networks: A Vertical Federated Learning Approach

  2024cited by this paper
• Optimized Bi-LSTM: a novel approach for attack detection in industrial IoT

  2024cited by this paper
• End-Edge-Cloud Collaboration-Based False Data Injection Attack Detection in Distribution Networks

  2024cited by this paper
• An Efficient Privacy-Enhancing Cross-Silo Federated Learning and Applications for False Data Injection Attack Detection in Smart Grids

  2023cited by this paper
• A Power System Disturbance Classification Method Robust to PMU Data Quality Issues

  2022cited by this paper
• Spatio-Temporal Correlation-Based False Data Injection Attack Detection Using Deep Convolutional Neural Network

  2022cited by this paper
• Experience-Driven Attack Design and Federated-Learning-Based Intrusion Detection in Industry 4.0

  2022cited by this paper
• Incentive edge-based federated learning for false data injection attack detection on power grid state estimation: A novel mechanism design approach

  2022cited by this paper
• Graph-based detection for false data injection attacks in power grid

  2022cited by this paper
• Transformers in Vision: A Survey

  2021cited by this paper
• Comprehensive Survey and Taxonomies of False Injection Attacks in Smart Grid: Attack Models, Targets, and Impacts

  2021cited by this paper
• Locational Detection of the False Data Injection Attack in a Smart Grid: A Multilabel Classification Approach

  2020cited by this paper
• Advances and Open Problems in Federated Learning

  2019cited by this paper
• A Survey of Physics-Based Attack Detection in Cyber-Physical Systems

  2018cited by this paper
• Federated Learning with Non-IID Data

  2018cited by this paper
• False data injection attacks against state estimation in electric power grids

  2011cited by this paper
• False data injection attacks against state estimation in electric power grids

  2009cited by this paper
• A Static State Estimation Approach Including Bad Data Detection and Identification in Power Systems

  2007cited by this paper
• A study of the behavior of several methods for balancing machine learning training data

  2004cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper

• No citing papers are available for this paper.