FedCognis: An Adaptive Federated Learning Framework for Secure Anomaly Detection in Industrial IoT-Enabled Cognitive Cities
Source abstract
Abstract
FedCognis is a secure and scalable federated learning framework designed for continuous anomaly detection in Industrial Internet of Things-enabled Cognitive Cities (IIoTCC). It introduces two key innovations: a Quantum Secure Authentication (QSA) mechanism for adversarial defense and integrity validation, and a Self-Attention Long Short-Term Memory (SALSTM) model for high-accuracy spatiotemporal anomaly detection. Addressing core challenges in traditional Federated Learning (FL)—such as model poisoning, communication overhead, and concept drift—FedCognis integrates dynamic trust-based aggregation and lightweight cryptographic verification to ensure secure, real-time operation across heterogeneous IIoT domains including utilities, public safety, and traffic systems. Evaluated on the WUSTL-IIoTCC-2021 dataset, FedCognis achieves 94.5% accuracy, 0.941 AUC for precision-recall, and 0.896 ROC-AUC, while reducing bandwidth consumption by 72%. The framework demonstrates sublinear computational complexity and a resilience score of 96.56% across six security dimensions. These results confirm FedCognis as a robust and adaptive anomaly detection solution suitable for deployment in large-scale cognitive urban infrastructures.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Network Security and Intrusion Detection · Smart Grid Security and Resilience · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (35)
Show source-provided references
1. Anomaly detection in QAR data using VAE-LSTM with multihead self-attention mechanism
2. A robust anomaly detection model for pumps based on the spectral residual with self-attention variational autoencoder10.1109/TII.2024.3381790 ↗
3. Time series anomaly detection in vehicle sensors using self-attention mechanisms10.1109/TITS.2024.3415435 ↗
4. Mishra · Artificial Neural Networks and Machine Learning—ICANN 2021 · 2021 · 129
5. ALAE: self-attention reconstruction network for multivariate time series anomaly identification10.1007/s00500-023-08467-4 ↗
6. Communication-efficient federated learning for anomaly detection in industrial Internet of Things
7. Multi-head attention based Bi-LSTM for anomaly detection in multivariate ticme-series of WSN
8. Najari · Advanced analytics and learning on temporal data · 2023 · 6610.1007/978-3-031-24378-3_5 ↗
9. You · Intelligent systems and applications · 2021 · 777
10. Generative adversarial networks for abnormal event detection in videos based on self-attention mechanism10.1109/ACCESS.2021.3110798 ↗
11. Federated learning for smart cities: a comprehensive survey
12. Integration of federated learning with IoT for smart cities applications: challenges and opportunities
13. Federated learning in smart city sensing: challenges and opportunities10.3390/s20216230 ↗
14. Anomaly detection techniques in smart cities: a review from a framework perspective
15. Poorazad SK, Benzaid C, Taleb T. A novel buffered federated learning framework for privacy-driven anomaly detection in IIoT. arXiv:2408.08722. 2024. doi:10.48550/arXiv.2408.08722.10.1109/GLOBECOM52923.2024.10901786 ↗
16. IoT in smart cities: a contemporary survey10.1016/j.gltp.2021.08.069 ↗
17. Toward accurate anomaly detection in industrial Internet of Things using hierarchical federated learning10.1109/JIOT.2021.3074382 ↗
18. Detecting cyberattacks using anomaly detection in industrial control systems: a federated learning approach10.1016/j.compind.2021.103509 ↗
19. Federated-learning-based anomaly detection for IoT security attacks10.1109/JIOT.2021.3077803 ↗
20. A federated learning-based approach for improving intrusion detection in industrial Internet of Things networks10.3390/network3010008 ↗
21. Enhancing IoT anomaly detection performance for federated learning10.1016/j.dcan.2022.02.007 ↗
22. Enhancing quantum security over federated learning via post-quantum cryptography
23. Fed-IIoT: a robust federated malware detection architecture in industrial IoT10.1109/TII.2020.3043458 ↗
24. Light-weight federated learning-based anomaly detection for time-series data in industrial control systems10.1016/j.compind.2022.103692 ↗
25. QFDSA: a quantum-secured federated learning system for smart grid dynamic security assessment10.1109/JIOT.2023.3321793 ↗
26. Quantum-empowered federated learning and 6G wireless networks for IoT security: concept, challenges and future directions10.1016/j.future.2024.06.023 ↗
27. Quantum-safe federated learning: enhancing data privacy and security
28. Enhancing IoT security through a green and sustainable federated learning platform: leveraging efficient encryption and the quondam signature algorithm10.3390/s23198090 ↗
29. Transitioning from federated learning to quantum federated learning in Internet of Things: a comprehensive survey10.1109/COMST.2024.3399612 ↗
30. OQFL: an optimized quantum-based federated learning framework for defending against adversarial attacks in intelligent transportation systems10.1109/TITS.2021.3130906 ↗
31. PQSF: post-quantum secure privacy-preserving federated learning10.1038/s41598-024-74377-6 ↗
32. Dynamic resource allocation framework for resilient and secure IoT communication using federated learning and quantum cryptography
33. A survey of deep anomaly detection in multivariate time series: taxonomy, applications, and directions10.3390/s25010190 ↗
34. A hybrid graph neural network and convolutional autoencoder for robust time series anomaly detection
35. Intrusion detection in IoT and IIoT: comparing lightweight machine learning techniques using TON_IoT, WUSTL-IIOT-2021, and EdgeIIoTset datasets10.1109/ACCESS.2025.3554083 ↗