Hybrid neural model boosts power grid cyberattack detection accuracy
Robust Industrial Cyber Physical Classification Using Neuromorphic Temporal Embeddings and Hybrid SNN XGBoost Under Machine Unlearning Attacks
Machine LearningCryptography and SecurityNeural and Evolutionary Computing
Summary
Power grids are more vulnerable to cyberattacks because of increased digital connections. The authors created a method combining two types of machine learning models—spiking neural networks and XGBoost—that is both fast and tough against data tampering attacks. Their system detects cyberattacks with very high accuracy on real datasets and keeps working well even when attackers try to confuse it by altering training data. This approach makes protecting critical power systems more reliable and efficient.
What this means in practice
- •For power grid operators: Detect cyberattacks on electrical distribution networks using a resilient and efficient hybrid learning model that maintains performance when updated with changing data.
- •For industrial control system engineers: Deploy lightweight intrusion detection on edge devices monitoring industrial networks with resistance to adversarial data manipulation.
Authors
Ammar Kamoona, Sajad Koushkbaghi, Mahdi Jalili, Peter McTaggart, Xinghuo Yu
Abstract
The digitalisation of electrical distribution networks has increased the exposure of power-grid infrastructure to cyber attacks. Existing intrusion detection systems (IDSs), however, often rely on computationally expensive deep learning models that are difficult to deploy at the edge. Periodic retraining also exposes these systems to machine unlearning attacks, where selective data removal can degrade detection performance. We propose a hybrid Spiking Neural Network (SNN) and XGBoost architecture that combines efficient temporal encoding with a lightweight classifier and provides structural resilience to such attacks. The SNN is trained once on clean data and used as a fixed feature extractor, while only the XGBoost classifier is retrained during model updates. Evaluated on two real-world public power-system datasets, the proposed method achieves 99.9\% accuracy (F1-macro 0.999) on the Synchrophasor dataset and 95.0\% accuracy (F1-macro 0.943) on the MSU/ORNL dataset, outperforming standalone baselines. Under selective label-flipping attacks, the hybrid model loses only 0.9\% F1-macro at 10\% poisoning and delays target-class collapse from 60\% to 70\% poisoning compared with raw models. These results demonstrate that neuromorphic temporal encoding can provide both accurate cyber-attack detection and improved resilience to data poisoning in cyber-physical systems.