Federated dual-attention temporal convolutional networks for privacy-preserving intrusion detection in EV charging infrastructure

The rapid growth of electric vehicle (EV) charging infrastructure has increased exposure to cyberattacks, while conventional centralized intrusion detection remains poorly suited to distributed and privacy-sensitive EVSE environments. This study proposes a federated learning framework based on a Dual-Attention Temporal Convolutional Network (DA-TCN) for collaborative cyberattack detection without centralized data sharing. The model combines dilated causal convolutions with channel and temporal attention to capture complex dependencies in multimodal EVSE telemetry. To improve federated optimization, we introduce Federated Stochastic Weight Averaging (FedSWA) and client-local mixup augmentation, which together enhance generalization and robustness across distributed clients. Evaluated on the CICEVSE2024 dataset, the proposed framework achieved 99.29% accuracy and 99.10% macro F1-score, outperforming a centralized baseline (98.79% accuracy) while maintaining perfect recall for benign and cryptojacking traffic. With an inference latency of 8.26 ms per batch and a model size of 4.07 MB, the framework is well suited for real-time edge deployment. A complementary Isolation Forest module provides unsupervised zero-day anomaly detection. These results demonstrate that federated learning can deliver accurate, lightweight, and deployment-ready intrusion detection for privacy-preserving EV charging infrastructure.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-16
DOI
https://doi.org/10.1038/s41598-026-67435-8
Citations
1
Primary Topic
Network Security and Intrusion Detection
Type
article
Field-Weighted Citation Impact
1.67

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Federated dual-attention temporal convolutional networks for privacy-preserving intrusion detection in EV charging infrastructure

Hitham Alhussian, Said Jadid Abdulkadir, Mohammed Gamal Ragab, Majdy Mohamed Eltayeb Eltahir et al.
1 citations
Scientific Reports
Network Security and Intrusion Detection
1.67
article

Federated dual-attention temporal convolutional networks for privacy-preserving intrusion detection in EV charging infrastructure

Hitham Alhussian, Said Jadid Abdulkadir, Mohammed Gamal Ragab, Majdy Mohamed Eltayeb Eltahir, Ayed Alwadain
article en
1 citations

Abstract

The rapid growth of electric vehicle (EV) charging infrastructure has increased exposure to cyberattacks, while conventional centralized intrusion detection remains poorly suited to distributed and privacy-sensitive EVSE environments. This study proposes a federated learning framework based on a Dual-Attention Temporal Convolutional Network (DA-TCN) for collaborative cyberattack detection without centralized data sharing. The model combines dilated causal convolutions with channel and temporal attention to capture complex dependencies in multimodal EVSE telemetry. To improve federated optimization, we introduce Federated Stochastic Weight Averaging (FedSWA) and client-local mixup augmentation, which together enhance generalization and robustness across distributed clients. Evaluated on the CICEVSE2024 dataset, the proposed framework achieved 99.29% accuracy and 99.10% macro F1-score, outperforming a centralized baseline (98.79% accuracy) while maintaining perfect recall for benign and cryptojacking traffic. With an inference latency of 8.26 ms per batch and a model size of 4.07 MB, the framework is well suited for real-time edge deployment. A complementary Isolation Forest module provides unsupervised zero-day anomaly detection. These results demonstrate that federated learning can deliver accurate, lightweight, and deployment-ready intrusion detection for privacy-preserving EV charging infrastructure.

Scientific ReportsVol. 16(1)
Universiti Teknologi Petronas (MY), King Saud University (SA), King Khalid University (SA)
King Saud University, Universiti Teknologi Petronas, King Khalid University, Yayasan UTP
Industry, innovation and infrastructure
Openalex Percentile: Top 19%
Network Security and Intrusion Detection
1.67
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon